SnowballTarget - second model

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5d4c7d4a5e8c0f00c74cd60fa4c2508eb0659607e4948deb15832e1ccacac8
+oid sha256:a8ec1fa0a8e813bce4ad86d2751761c9557a55a26b8fa32c85c9457bba5fdf59
 size 645119

SnowballTarget/SnowballTarget-1408.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bac96f70de7d9f346bd05cfd0425a8509aed910bb20046d77b4d27f6654409b3
-size 1285728

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c63aa2b5c0f419c3f54dc809b1e01c0125d35504601e68a8c24ad1e95b7497
+oid sha256:e778d105fbf5a2f8b7c8a8cf082d06ff2f37d6e3ae14ec0d1088b044fc0b86ba
 size 645119

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046f4a0d0165a428ad06d0e2add83306a36b114fe2aaf01932ac011c5199da55
+oid sha256:18da9fb5c684527f7e20947aafd21450c8eee0ed06b3fe3b2e044d729c50c5eb
 size 3845312

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5d4c7d4a5e8c0f00c74cd60fa4c2508eb0659607e4948deb15832e1ccacac8
+oid sha256:b6864993fbff634a20e4d3e184db3e3bc575b53db9e6578a07335229e84a00d6
 size 645119

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa970b63d53b6592c74c7a462271950b80d7bf0a86cb2c6e3babfe0aee34984
+oid sha256:d712f09d939ed3ce15b4288ce253c19230f169f44128575d38abd411dcf15818
 size 3845312

SnowballTarget/{SnowballTarget-125592.onnx → SnowballTarget-249880.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215bbdd5e692ee7ade626e82e19035a135ed39176e60b1646eff782d3776b5fe
+oid sha256:a2a1b842815a817a25936e4db1802b209dbdfd42eb753ecd5abe569620f6a6b8
 size 645119

SnowballTarget/{SnowballTarget-200368.pt → SnowballTarget-249880.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d8e0cc10c9f41f330802cf4f8a2958a4678e6494c19f9da0ea611b3a981dd4
+oid sha256:c4425703647d39fdd3dc5a5286b3a997db6058fd94c8ceaa4dc0835e90165e38
 size 3845312

SnowballTarget/{SnowballTarget-200368.onnx → SnowballTarget-299968.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5d4c7d4a5e8c0f00c74cd60fa4c2508eb0659607e4948deb15832e1ccacac8
+oid sha256:8b6b3a71b0cae734fe4720a12a6674d89e2ea4f93b7ca75478dde453c6ef0a65
 size 645119

SnowballTarget/{SnowballTarget-125592.pt → SnowballTarget-299968.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcbbb66c41f20d93074c389f74b55a5d9793c58108fc2e065736bba1c8a66d4
+oid sha256:f46c549641165b229e2e610e107970a4e67c1b5eae185e4105f9386afdef84ca
 size 3845312

SnowballTarget/{SnowballTarget-1408.onnx → SnowballTarget-349928.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:579bc1cc9e4a5129349a0d054364ea21bcd896a384f0af181b2dee8a9d89d73f
+oid sha256:3602998f6c4001791276db01468b0c8d823008ecd744276e9f36ad64f83d247a
 size 645119

SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-349928.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a854d81907d5b5dc9263059b3db9bc4d34151fd470ebc1602f00fb45d95a3e88
+oid sha256:053cfc94c9ba686fc0595b5753a04400841066946b0c4594ba9c4bf327770896
 size 3845312

SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-399968.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f89b74c62b4cef4c7c8ea8b0620a4d18df79e6582564dd0e45a748952c8f57
+oid sha256:fc132014ce7489f75359585b48c8061d4ab5ea4a3ec37746071f11f27f3e9a2e
 size 645119

SnowballTarget/{SnowballTarget-99960.pt → SnowballTarget-399968.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c4e5bc31668c596264d68a59ebf9fe0a286df4e18e75b5bab6a8fd145fee488
+oid sha256:19bff0c2c82809c32c687e93487f80b83193599e7d60c60b4d5abf2411ba4c2a
 size 3845312

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc3b30a4db62c55913998b67e010e16dd439a0524869b0c6fd9b2eda61fc7011
+size 645119

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192499951d4b0cc404bb21b6cdab6df70edae4bba5c4022996ebd973c41dae89
+size 3845312

SnowballTarget/SnowballTarget-499912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ec1fa0a8e813bce4ad86d2751761c9557a55a26b8fa32c85c9457bba5fdf59
+size 645119

SnowballTarget/SnowballTarget-499912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e695ce1b687ea703e015b5e8940374eba8abdd83608766e960011d3a10d892a5
+size 3845312

SnowballTarget/SnowballTarget-500808.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ec1fa0a8e813bce4ad86d2751761c9557a55a26b8fa32c85c9457bba5fdf59
+size 645119

SnowballTarget/SnowballTarget-500808.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4440433e37a7f5465b3a1d55efb16ee5d6f48e320520089a6ba95fc3f3101bd3
+size 3845312

SnowballTarget/SnowballTarget-99896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d60d977635b86ea25fb72a0adb5c6dc3f42ed4c256ca948ddf6e0c9f7c21166
+size 645119

SnowballTarget/SnowballTarget-99896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7fb36b5d9e832d960bfbb90f12165fc1289d4bc6744bf2fec355a399e258d3
+size 3845312

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c25cd4e017767ce894ddcbeab83b28091712adadcfd253932fa03ae33f1aa73b
-size 645119

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d8e0cc10c9f41f330802cf4f8a2958a4678e6494c19f9da0ea611b3a981dd4
+oid sha256:4440433e37a7f5465b3a1d55efb16ee5d6f48e320520089a6ba95fc3f3101bd3
 size 3845312

SnowballTarget/events.out.tfevents.1673952569.8a42fd845b75.6872.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:18bc4029a11f0ebbd87f73b7aed687fa9099fed276f9dfcba52bcebcfb968157
-size 7737

SnowballTarget/{events.out.tfevents.1673952243.8a42fd845b75.5303.0 → events.out.tfevents.1673953149.8a42fd845b75.9878.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2d93e8ef2b487acb168530b260605856c427043786026d41e43b8e934e3fa9
-size 17301
+oid sha256:20299a7a959232a5562571916cc50b7380b2175446b0b56e33a1302b39f4f992
+size 53958

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 4096, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "checkpoint_interval": 50000, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 8192, "learning_rate": 0.001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "checkpoint_interval": 50000, "max_steps": 500000, "time_horizon": 128, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,9 +3,9 @@ behaviors:
   SnowballTarget:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 4096
-      learning_rate: 0.0005
+      batch_size: 256
+      buffer_size: 8192
+      learning_rate: 0.001
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -23,7 +23,7 @@ behaviors:
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.99
+        gamma: 0.95
         strength: 1.0
         network_settings:
           normalize: false
@@ -36,8 +36,8 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     checkpoint_interval: 50000
-    max_steps: 200000
-    time_horizon: 64
+    max_steps: 500000
+    time_horizon: 128
     summary_freq: 10000
     threaded: true
     self_play: null
@@ -62,10 +62,10 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
-  resume: true
+  resume: false
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.073 seconds
+- Completed reload, in  0.081 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.618724 ms
+UnloadTime: 0.653365 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -50,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 2006 frames, [16.0 KB-32.0 KB]: 34 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 13433 frames, [16.0 KB-32.0 KB]: 227 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -166,19 +166,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 33
+  Peak main deferred allocation count 40
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 2041 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 11923 frames, [8.0 MB-16.0 MB]: 1738 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.6 MB
+      Peak Allocated memory 9.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 2041 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13661 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.8 MB
@@ -210,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1993 frames, [64.0 KB-128.0 KB]: 48 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13084 frames, [64.0 KB-128.0 KB]: 577 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 66.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 2041 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13661 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 2041 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13661 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 2040 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13660 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -246,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 2041 frames
+      Peak usage frame count: [0-1.0 KB]: 13661 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 2041 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 13661 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,220 +2,220 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 1.328168511390686,
-            "min": 1.328168511390686,
-            "max": 1.6884623765945435,
-            "count": 8
+            "value": 1.135367512702942,
+            "min": 1.135367512702942,
+            "max": 2.887923240661621,
+            "count": 50
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 13543.333984375,
-            "min": 8617.912109375,
-            "max": 16077.0927734375,
-            "count": 8
+            "value": 11589.83203125,
+            "min": 10198.53515625,
+            "max": 31862.45703125,
+            "count": 50
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 129992.0,
-            "max": 199984.0,
-            "count": 8
+            "value": 499912.0,
+            "min": 9952.0,
+            "max": 499912.0,
+            "count": 50
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 129992.0,
-            "max": 199984.0,
-            "count": 8
+            "value": 499912.0,
+            "min": 9952.0,
+            "max": 499912.0,
+            "count": 50
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.007621765136719,
-            "min": 9.204183578491211,
-            "max": 12.007621765136719,
-            "count": 8
+            "value": 2.7458341121673584,
+            "min": 0.106269471347332,
+            "max": 2.7458341121673584,
+            "count": 50
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2341.486328125,
-            "min": 736.334716796875,
-            "max": 2408.5126953125,
-            "count": 8
+            "value": 277.3292541503906,
+            "min": 10.308138847351074,
+            "max": 278.6896057128906,
+            "count": 50
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 8
+            "count": 50
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 8756.0,
-            "min": 4378.0,
+            "min": 8756.0,
             "max": 10945.0,
-            "count": 8
+            "count": 50
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.90909090909091,
-            "min": 22.26923076923077,
-            "max": 25.09090909090909,
-            "count": 8
+            "value": 27.037735849056602,
+            "min": 3.0681818181818183,
+            "max": 27.434782608695652,
+            "count": 50
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1096.0,
-            "min": 315.0,
-            "max": 1380.0,
-            "count": 8
+            "value": 1433.0,
+            "min": 135.0,
+            "max": 1457.0,
+            "count": 50
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.90909090909091,
-            "min": 22.26923076923077,
-            "max": 25.09090909090909,
-            "count": 8
+            "value": 27.037735849056602,
+            "min": 3.0681818181818183,
+            "max": 27.434782608695652,
+            "count": 50
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1096.0,
-            "min": 315.0,
-            "max": 1380.0,
-            "count": 8
+            "value": 1433.0,
+            "min": 135.0,
+            "max": 1457.0,
+            "count": 50
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.0660925427240299,
-            "min": 0.06426675086982096,
-            "max": 0.07081947505842917,
-            "count": 8
+            "value": 0.05115493647856912,
+            "min": 0.04354346607116681,
+            "max": 0.056254119427039236,
+            "count": 50
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.1321850854480598,
-            "min": 0.06426675086982096,
-            "max": 0.21118983861661572,
-            "count": 8
+            "value": 0.05115493647856912,
+            "min": 0.04354346607116681,
+            "max": 0.10711522025230806,
+            "count": 50
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.20692843010320383,
-            "min": 0.20692843010320383,
-            "max": 0.24697394416187748,
-            "count": 8
+            "value": 0.1038912947563564,
+            "min": 0.06381678456331001,
+            "max": 0.16697393173680586,
+            "count": 50
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.41385686020640766,
-            "min": 0.24697394416187748,
-            "max": 0.7215860576314084,
-            "count": 8
+            "value": 0.1038912947563564,
+            "min": 0.06381678456331001,
+            "max": 0.2940784593715387,
+            "count": 50
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 1.5580096883999985e-05,
-            "min": 1.5580096883999985e-05,
-            "max": 0.00017508006498399996,
-            "count": 8
+            "value": 1.5984098401599997e-05,
+            "min": 1.5984098401599997e-05,
+            "max": 0.00098240000176,
+            "count": 50
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.116019376799997e-05,
-            "min": 3.116019376799997e-05,
-            "max": 0.00031716013656799994,
-            "count": 8
+            "value": 1.5984098401599997e-05,
+            "min": 1.5984098401599997e-05,
+            "max": 0.0017391680260832,
+            "count": 50
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10311599999999999,
-            "min": 0.10311599999999999,
-            "max": 0.13501600000000002,
-            "count": 8
+            "value": 0.10159840000000002,
+            "min": 0.10159840000000002,
+            "max": 0.19823999999999997,
+            "count": 50
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.20623199999999997,
-            "min": 0.13501600000000002,
-            "max": 0.35224799999999995,
-            "count": 8
+            "value": 0.10159840000000002,
+            "min": 0.10159840000000002,
+            "max": 0.3739168,
+            "count": 50
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.00016548839999999982,
-            "min": 0.00016548839999999982,
-            "max": 0.0017572984000000002,
-            "count": 8
+            "value": 8.976015999999999e-05,
+            "min": 8.976015999999999e-05,
+            "max": 0.004912176000000002,
+            "count": 50
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.00033097679999999965,
-            "min": 0.00033097679999999965,
-            "max": 0.0031852568000000003,
-            "count": 8
+            "value": 8.976015999999999e-05,
+            "min": 8.976015999999999e-05,
+            "max": 0.008698448319999998,
+            "count": 50
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 8
+            "count": 50
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 8
+            "count": 50
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673952566",
+        "start_time_seconds": "1673953146",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673952749"
+        "end_time_seconds": "1673954277"
     },
-    "total": 183.44327956799998,
+    "total": 1130.721411611,
     "count": 1,
-    "self": 0.38690096899995297,
+    "self": 0.3841987599994354,
     "children": {
         "run_training.setup": {
-            "total": 0.11145493399999395,
+            "total": 0.11357385500014061,
             "count": 1,
-            "self": 0.11145493399999395
+            "self": 0.11357385500014061
         },
         "TrainerController.start_learning": {
-            "total": 182.94492366500003,
+            "total": 1130.2236389960003,
             "count": 1,
-            "self": 0.21657700199239116,
+            "self": 1.3224685849850175,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.098904782999853,
+                    "total": 6.175763149999966,
                     "count": 1,
-                    "self": 6.098904782999853
+                    "self": 6.175763149999966
                 },
                 "TrainerController.advance": {
-                    "total": 176.50930990300776,
-                    "count": 6802,
-                    "self": 0.10504824200597795,
+                    "total": 1122.606961164015,
+                    "count": 45534,
+                    "self": 0.6573774920002506,
                     "children": {
                         "env_step": {
-                            "total": 176.40426166100178,
-                            "count": 6802,
-                            "self": 128.7467460399805,
+                            "total": 1121.9495836720148,
+                            "count": 45534,
+                            "self": 753.3429917339977,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 47.54695558100752,
-                                    "count": 6802,
-                                    "self": 0.506306558009328,
+                                    "total": 367.9117610980047,
+                                    "count": 45534,
+                                    "self": 3.362679239029603,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 47.040649022998196,
-                                            "count": 6802,
-                                            "self": 10.416061452002168,
+                                            "total": 364.5490818589751,
+                                            "count": 45534,
+                                            "self": 79.10298805595357,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 36.62458757099603,
-                                                    "count": 6802,
-                                                    "self": 36.62458757099603
+                                                    "total": 285.44609380302154,
+                                                    "count": 45534,
+                                                    "self": 285.44609380302154
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.11056004001375186,
-                                    "count": 6802,
+                                    "total": 0.6948308400124006,
+                                    "count": 45534,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 182.45991812600755,
-                                            "count": 6802,
+                                            "total": 1126.9902016269893,
+                                            "count": 45534,
                                             "is_parallel": true,
-                                            "self": 99.34957993200283,
+                                            "self": 565.6729538380469,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +224,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0017766769999525422,
+                                                            "total": 0.0018085649999193265,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005972249998649204,
+                                                            "self": 0.0005987880003885948,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0011794520000876219,
+                                                                    "total": 0.0012097769995307317,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0011794520000876219
+                                                                    "self": 0.0012097769995307317
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04119560999993155,
+                                                            "total": 0.03667948699967383,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005442609999590786,
+                                                            "self": 0.00035762999914368265,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003620250001858949,
+                                                                    "total": 0.000469673000225157,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003620250001858949
+                                                                    "self": 0.000469673000225157
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03838651499995649,
+                                                                    "total": 0.0343268070000704,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03838651499995649
+                                                                    "self": 0.0343268070000704
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019028089998300857,
+                                                                    "total": 0.0015253770002345846,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004959179996149032,
+                                                                    "self": 0.00040654099984749337,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014068910002151824,
+                                                                            "total": 0.0011188360003870912,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014068910002151824
+                                                                            "self": 0.0011188360003870912
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +274,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 83.11033819400473,
-                                                    "count": 6801,
+                                                    "total": 561.3172477889425,
+                                                    "count": 45533,
                                                     "is_parallel": true,
-                                                    "self": 3.0566140609896593,
+                                                    "self": 20.925553688022774,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 1.8816506050081898,
-                                                            "count": 6801,
+                                                            "total": 12.946825961988452,
+                                                            "count": 45533,
                                                             "is_parallel": true,
-                                                            "self": 1.8816506050081898
+                                                            "self": 12.946825961988452
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 67.01576045099796,
-                                                            "count": 6801,
+                                                            "total": 445.0801878959833,
+                                                            "count": 45533,
                                                             "is_parallel": true,
-                                                            "self": 67.01576045099796
+                                                            "self": 445.0801878959833
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 11.156313077008917,
-                                                            "count": 6801,
+                                                            "total": 82.364680242948,
+                                                            "count": 45533,
                                                             "is_parallel": true,
-                                                            "self": 2.3903602610273538,
+                                                            "self": 16.67430063593565,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 8.765952815981564,
-                                                                    "count": 68010,
+                                                                    "total": 65.69037960701235,
+                                                                    "count": 455330,
                                                                     "is_parallel": true,
-                                                                    "self": 8.765952815981564
+                                                                    "self": 65.69037960701235
                                                                 }
                                                             }
                                                         }
@@ -316,9 +316,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.488800004764926e-05,
+                    "total": 4.785600003742729e-05,
                     "count": 1,
-                    "self": 4.488800004764926e-05,
+                    "self": 4.785600003742729e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -327,36 +327,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 175.15293219802106,
-                                    "count": 160925,
+                                    "total": 1113.9459555088974,
+                                    "count": 1033906,
                                     "is_parallel": true,
-                                    "self": 4.2363684649897095,
+                                    "self": 26.339789770306652,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 110.09657355303102,
-                                            "count": 160925,
+                                            "total": 670.5739063215933,
+                                            "count": 1033906,
                                             "is_parallel": true,
-                                            "self": 109.6392081670308,
+                                            "self": 668.849687068594,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.4573653860002196,
-                                                    "count": 2,
+                                                    "total": 1.724219252999319,
+                                                    "count": 10,
                                                     "is_parallel": true,
-                                                    "self": 0.4573653860002196
+                                                    "self": 1.724219252999319
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 60.81999018000033,
-                                            "count": 16,
+                                            "total": 417.0322594169975,
+                                            "count": 56,
                                             "is_parallel": true,
-                                            "self": 24.29063101199381,
+                                            "self": 179.76885711297064,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 36.52935916800652,
-                                                    "count": 2715,
+                                                    "total": 237.26340230402684,
+                                                    "count": 9505,
                                                     "is_parallel": true,
-                                                    "self": 36.52935916800652
+                                                    "self": 237.26340230402684
                                                 }
                                             }
                                         }
@@ -367,14 +367,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12008708899998055,
+                    "total": 0.11839824100024998,
                     "count": 1,
-                    "self": 0.0010848530000657775,
+                    "self": 0.0008372170004804502,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.11900223599991477,
+                            "total": 0.11756102399976953,
                             "count": 1,
-                            "self": 0.11900223599991477
+                            "self": 0.11756102399976953
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,67 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 12.272727272727273,
-                "creation_time": 1673952364.9932427,
+                "steps": 99896,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99896.onnx",
+                "reward": 15.363636363636363,
+                "creation_time": 1673953375.902,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-99896.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 20.363636363636363,
-                "creation_time": 1673952484.5346525,
+                "steps": 149984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 22.09090909090909,
+                "creation_time": 1673953491.7287333,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
-                "steps": 126104,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-125592.onnx",
-                "reward": 22.318181818181817,
-                "creation_time": 1673952546.7718027,
+                "steps": 199984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 22.75609756097561,
+                "creation_time": 1673953599.200578,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-125592.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.136363636363637,
-                "creation_time": 1673952631.1833293,
+                "steps": 249880,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-249880.onnx",
+                "reward": 24.818181818181817,
+                "creation_time": 1673953713.4827852,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-249880.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 24.636363636363637,
-                "creation_time": 1673952749.3621132,
+                "steps": 299968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1673953829.2000349,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349928,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-349928.onnx",
+                "reward": 26.204545454545453,
+                "creation_time": 1673953939.8303313,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-349928.pt"
+                ]
+            },
+            {
+                "steps": 399968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-399968.onnx",
+                "reward": 25.77777777777778,
+                "creation_time": 1673954052.8616538,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-399968.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1673954165.580728,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499912,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-499912.onnx",
+                "reward": 27.136363636363637,
+                "creation_time": 1673954276.701201,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-499912.pt"
                 ]
             },
             {
-                "steps": 200368,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200368.onnx",
-                "reward": 24.636363636363637,
-                "creation_time": 1673952749.5381525,
+                "steps": 500808,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-500808.onnx",
+                "reward": 27.136363636363637,
+                "creation_time": 1673954276.9201777,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200368.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-500808.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200368,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 24.636363636363637,
-            "creation_time": 1673952749.5381525,
+            "steps": 500808,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 27.136363636363637,
+            "creation_time": 1673954276.9201777,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200368.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-500808.pt"
             ]
         }
     },