Another bad model

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67d32c5d2ea47f0d6c187d122205449db2e0dc7eaf1dd7e9aac80efc73994e5
+oid sha256:e363a184531047b5f01a5619398e327eb42c52a3db84b394d8e7e4a49f2eea79
 size 646532

SnowballTarget/{SnowballTarget-10208.onnx → SnowballTarget-14992.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67d32c5d2ea47f0d6c187d122205449db2e0dc7eaf1dd7e9aac80efc73994e5
+oid sha256:35b09dc2d1017f72a391b2f883f8b08901a314c90daa473550d844d242a30439
 size 646532

SnowballTarget/{SnowballTarget-10208.pt → SnowballTarget-14992.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3da68f3da6bc688f4f3608b38dfeb6213253a7dbe40b194cc031da7bda13e3f
+oid sha256:fd7d25870fd41cc01e086a889a8dcc94b2d604391540b11e550d46dbe243c695
 size 3843968

SnowballTarget/SnowballTarget-19992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e363a184531047b5f01a5619398e327eb42c52a3db84b394d8e7e4a49f2eea79
+size 646532

SnowballTarget/SnowballTarget-19992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52aa8727aae3d33441da00f016ee51d9c39e74510ce1407b09c37531915cdb60
+size 3843968

SnowballTarget/SnowballTarget-20376.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e363a184531047b5f01a5619398e327eb42c52a3db84b394d8e7e4a49f2eea79
+size 646532

SnowballTarget/SnowballTarget-20376.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b703ef33b62bb1d93f06fd1772ca0aec32738caf7ff8923c382145a4b1876f88
+size 3843968

SnowballTarget/SnowballTarget-4976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447935321628ae3099b12beb4cf83627be06fdbb034ff9fdef384b7ff23f3353
+size 646532

SnowballTarget/SnowballTarget-4976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210be07b0533ad6bc54d3f8271f0116b3b082bbc29a6708d6117001869f346f3
+size 3843968

SnowballTarget/SnowballTarget-9952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da0f1afe2f5b2a014652a68c6935ec4ebcb03659f38ba741b0471fbe0b67449
+size 646532

SnowballTarget/SnowballTarget-9952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d7bd1cfe1e2f802a3af56be196946690da07317232fa8bac44c16bd5be599e
+size 3843968

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3da68f3da6bc688f4f3608b38dfeb6213253a7dbe40b194cc031da7bda13e3f
+oid sha256:b703ef33b62bb1d93f06fd1772ca0aec32738caf7ff8923c382145a4b1876f88
 size 3843968

SnowballTarget/{events.out.tfevents.1683279631.c88edd4d651c.5646.0 → events.out.tfevents.1683279867.c88edd4d651c.6973.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3b53d03eb82f9479173773d19b6af8bc1d45460ae2424a13dad5d1a3a3d149f
-size 15420
+oid sha256:70ef5fbffb1f8810f6fa5b78fc6203774aea50447610168d66d9eccdf17b8475
+size 39676

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "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, "even_checkpoints": false, "max_steps": 10000, "time_horizon": 64, "summary_freq": 1000, "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": false, "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": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 5000, "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, "even_checkpoints": false, "max_steps": 20000, "time_horizon": 64, "summary_freq": 1000, "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

@@ -14,7 +14,7 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 50000
+    checkpoint_interval: 5000
     network_settings:
       normalize: false
       hidden_units: 256
@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 10000
+    max_steps: 20000
     time_horizon: 64
     summary_freq: 1000
     threaded: true
@@ -64,7 +64,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2642:(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  0.082 seconds
+- Completed reload, in  0.088 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)
@@ -45,7 +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: 0.710605 ms
+UnloadTime: 0.906578 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.
@@ -53,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 275 frames, [16.0 KB-32.0 KB]: 4 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 553 frames, [16.0 KB-32.0 KB]: 9 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
@@ -169,22 +166,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 28
+  Peak main deferred allocation count 34
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 280 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 563 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.7 MB
+      Peak Allocated memory 5.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 280 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 563 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.2 MB
+      Peak Allocated memory 17.9 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 254 frames, [64.0 KB-128.0 KB]: 26 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 476 frames, [64.0 KB-128.0 KB]: 87 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 280 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 563 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 280 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 563 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]: 279 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 562 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
@@ -249,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 280 frames
+      Peak usage frame count: [0-1.0 KB]: 563 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]: 280 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 563 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 2.8599154949188232,
-            "min": 2.8599154949188232,
-            "max": 2.8903441429138184,
-            "count": 10
+            "value": 2.801654815673828,
+            "min": 2.7997958660125732,
+            "max": 2.890307903289795,
+            "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 1950.46240234375,
-            "min": 1950.46240234375,
-            "max": 4191.31298828125,
-            "count": 10
+            "value": 4222.09375,
+            "min": 1879.363525390625,
+            "max": 4296.60595703125,
+            "count": 20
         },
         "SnowballTarget.Step.mean": {
-            "value": 9952.0,
+            "value": 19992.0,
             "min": 960.0,
-            "max": 9952.0,
-            "count": 10
+            "max": 19992.0,
+            "count": 20
         },
         "SnowballTarget.Step.sum": {
-            "value": 9952.0,
+            "value": 19992.0,
             "min": 960.0,
-            "max": 9952.0,
-            "count": 10
+            "max": 19992.0,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7541240453720093,
-            "min": -0.07974924892187119,
-            "max": 0.7541240453720093,
-            "count": 10
+            "value": 1.4630661010742188,
+            "min": 0.054035332053899765,
+            "max": 1.4630661010742188,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 11.311861038208008,
-            "min": -1.2458819150924683,
-            "max": 16.76790428161621,
-            "count": 10
+            "value": 38.03971862792969,
+            "min": 0.8137731552124023,
+            "max": 38.03971862792969,
+            "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 20
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 4
+            "count": 9
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 2189.0,
             "min": 2189.0,
             "max": 2189.0,
-            "count": 4
+            "count": 9
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07809640580386508,
-            "min": 0.05779704182664407,
-            "max": 0.08323019002273213,
-            "count": 4
+            "value": 0.07258494993313398,
+            "min": 0.05907012469833717,
+            "max": 0.08416848606886525,
+            "count": 9
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.07809640580386508,
-            "min": 0.05779704182664407,
-            "max": 0.08323019002273213,
-            "count": 4
+            "value": 0.07258494993313398,
+            "min": 0.05907012469833717,
+            "max": 0.08416848606886525,
+            "count": 9
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.16764303457503224,
-            "min": 0.07911297034782667,
-            "max": 0.16764303457503224,
-            "count": 4
+            "value": 0.21661260315016204,
+            "min": 0.06433110148645937,
+            "max": 0.21661260315016204,
+            "count": 9
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.16764303457503224,
-            "min": 0.07911297034782667,
-            "max": 0.16764303457503224,
-            "count": 4
+            "value": 0.21661260315016204,
+            "min": 0.06433110148645937,
+            "max": 0.21661260315016204,
+            "count": 9
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 3.864008712000001e-05,
-            "min": 3.864008712000001e-05,
-            "max": 0.00023664002112000002,
-            "count": 4
+            "value": 4.320098559999991e-06,
+            "min": 4.320098559999991e-06,
+            "max": 0.00026832001056,
+            "count": 9
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.864008712000001e-05,
-            "min": 3.864008712000001e-05,
-            "max": 0.00023664002112000002,
-            "count": 4
+            "value": 4.320098559999991e-06,
+            "min": 4.320098559999991e-06,
+            "max": 0.00026832001056,
+            "count": 9
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.11287999999999998,
-            "min": 0.11287999999999998,
-            "max": 0.17888,
-            "count": 4
+            "value": 0.10144,
+            "min": 0.10144,
+            "max": 0.18944000000000003,
+            "count": 9
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.11287999999999998,
-            "min": 0.11287999999999998,
-            "max": 0.17888,
-            "count": 4
+            "value": 0.10144,
+            "min": 0.10144,
+            "max": 0.18944000000000003,
+            "count": 9
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0006527120000000002,
-            "min": 0.0006527120000000002,
-            "max": 0.003946112000000001,
-            "count": 4
+            "value": 8.185599999999986e-05,
+            "min": 8.185599999999986e-05,
+            "max": 0.0044730559999999996,
+            "count": 9
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0006527120000000002,
-            "min": 0.0006527120000000002,
-            "max": 0.003946112000000001,
-            "count": 4
+            "value": 8.185599999999986e-05,
+            "min": 8.185599999999986e-05,
+            "max": 0.0044730559999999996,
+            "count": 9
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 4.2727272727272725,
-            "min": 2.090909090909091,
-            "max": 4.2727272727272725,
-            "count": 4
+            "value": 6.363636363636363,
+            "min": 1.9090909090909092,
+            "max": 6.363636363636363,
+            "count": 10
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 47.0,
-            "min": 23.0,
-            "max": 47.0,
-            "count": 4
+            "value": 70.0,
+            "min": 6.0,
+            "max": 70.0,
+            "count": 10
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 4.2727272727272725,
-            "min": 2.090909090909091,
-            "max": 4.2727272727272725,
-            "count": 4
+            "value": 6.363636363636363,
+            "min": 1.9090909090909092,
+            "max": 6.363636363636363,
+            "count": 10
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 47.0,
-            "min": 23.0,
-            "max": 47.0,
-            "count": 4
+            "value": 70.0,
+            "min": 6.0,
+            "max": 70.0,
+            "count": 10
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1683279630",
+        "start_time_seconds": "1683279866",
         "python_version": "3.10.11 (main, Apr  5 2023, 14:15:10) [GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "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": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1683279659"
+        "end_time_seconds": "1683279920"
     },
-    "total": 28.752500829999917,
+    "total": 53.57713409799999,
     "count": 1,
-    "self": 0.43344727799967586,
+    "self": 0.6897066520000408,
     "children": {
         "run_training.setup": {
-            "total": 0.04060176200005117,
+            "total": 0.03874288199995135,
             "count": 1,
-            "self": 0.04060176200005117
+            "self": 0.03874288199995135
         },
         "TrainerController.start_learning": {
-            "total": 28.27845179000019,
+            "total": 52.848684563999996,
             "count": 1,
-            "self": 0.050298429999656946,
+            "self": 0.07185487300466775,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.218312665999974,
+                    "total": 3.8306307689999812,
                     "count": 1,
-                    "self": 5.218312665999974
+                    "self": 3.8306307689999812
                 },
                 "TrainerController.advance": {
-                    "total": 22.848813578000545,
-                    "count": 931,
-                    "self": 0.012539371995217152,
+                    "total": 48.78620302299532,
+                    "count": 1874,
+                    "self": 0.028755773993907496,
                     "children": {
                         "env_step": {
-                            "total": 22.836274206005328,
-                            "count": 931,
-                            "self": 16.601151568004525,
+                            "total": 48.757447249001416,
+                            "count": 1874,
+                            "self": 35.38897093799119,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 6.222414203002245,
-                                    "count": 931,
-                                    "self": 0.08063506700136713,
+                                    "total": 13.341887148011892,
+                                    "count": 1874,
+                                    "self": 0.1632166190136104,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 6.141779136000878,
-                                            "count": 931,
-                                            "self": 6.141779136000878
+                                            "total": 13.178670528998282,
+                                            "count": 1874,
+                                            "self": 13.178670528998282
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.012708434998558005,
-                                    "count": 931,
+                                    "total": 0.02658916299833436,
+                                    "count": 1874,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 28.047405189997335,
-                                            "count": 931,
+                                            "total": 52.55357760500169,
+                                            "count": 1874,
                                             "is_parallel": true,
-                                            "self": 15.407515427995804,
+                                            "self": 26.85210147700036,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.007735242000080689,
+                                                            "total": 0.0017832309999903373,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.006233841999573997,
+                                                            "self": 0.0004351480001787422,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015014000005066919,
+                                                                    "total": 0.001348082999811595,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015014000005066919
+                                                                    "self": 0.001348082999811595
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05210185700002512,
+                                                            "total": 0.03532547099985095,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000565791999861176,
+                                                            "self": 0.0005585599999449187,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044090400001550734,
+                                                                    "total": 0.00031621499988432333,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044090400001550734
+                                                                    "self": 0.00031621499988432333
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0485687059999691,
+                                                                    "total": 0.032542380999984744,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0485687059999691
+                                                                    "self": 0.032542380999984744
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0025264550001793395,
+                                                                    "total": 0.0019083150000369642,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003929669996978191,
+                                                                    "self": 0.0003870910002206074,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0021334880004815204,
+                                                                            "total": 0.0015212239998163568,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0021334880004815204
+                                                                            "self": 0.0015212239998163568
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 12.63988976200153,
-                                                    "count": 930,
+                                                    "total": 25.70147612800133,
+                                                    "count": 1873,
                                                     "is_parallel": true,
-                                                    "self": 0.49495689800164655,
+                                                    "self": 1.013799609001353,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.2655887619987425,
-                                                            "count": 930,
+                                                            "total": 0.5504755020058383,
+                                                            "count": 1873,
                                                             "is_parallel": true,
-                                                            "self": 0.2655887619987425
+                                                            "self": 0.5504755020058383
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 10.152741015001766,
-                                                            "count": 930,
+                                                            "total": 20.62665870399428,
+                                                            "count": 1873,
                                                             "is_parallel": true,
-                                                            "self": 10.152741015001766
+                                                            "self": 20.62665870399428
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 1.7266030869993756,
-                                                            "count": 930,
+                                                            "total": 3.51054231299986,
+                                                            "count": 1873,
                                                             "is_parallel": true,
-                                                            "self": 0.33530688799078234,
+                                                            "self": 0.6997057490038969,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 1.3912961990085932,
-                                                                    "count": 9300,
+                                                                    "total": 2.810836563995963,
+                                                                    "count": 18730,
                                                                     "is_parallel": true,
-                                                                    "self": 1.3912961990085932
+                                                                    "self": 2.810836563995963
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.0002213340001162578,
+                    "total": 0.00022436899985223135,
                     "count": 1,
-                    "self": 0.0002213340001162578,
+                    "self": 0.00022436899985223135,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,28 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 22.66529308300619,
-                                    "count": 24889,
+                                    "total": 48.43041554401316,
+                                    "count": 43769,
                                     "is_parallel": true,
-                                    "self": 0.5348454970010152,
+                                    "self": 1.0189565230202788,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 13.72370477100526,
-                                            "count": 24889,
+                                            "total": 27.539691928992625,
+                                            "count": 43769,
                                             "is_parallel": true,
-                                            "self": 13.72370477100526
+                                            "self": 26.128432137992377,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.4112597910002478,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 1.4112597910002478
+                                                }
+                                            }
                                         },
                                         "_update_policy": {
-                                            "total": 8.406742814999916,
-                                            "count": 4,
+                                            "total": 19.871767092000255,
+                                            "count": 9,
                                             "is_parallel": true,
-                                            "self": 3.07030464500167,
+                                            "self": 7.773654529000169,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 5.336438169998246,
-                                                    "count": 201,
+                                                    "total": 12.098112563000086,
+                                                    "count": 456,
                                                     "is_parallel": true,
-                                                    "self": 5.336438169998246
+                                                    "self": 12.098112563000086
                                                 }
                                             }
                                         }
@@ -352,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1608057819998976,
+                    "total": 0.15977153000017097,
                     "count": 1,
-                    "self": 0.0008927029998631042,
+                    "self": 0.0008451560001958569,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.15991307900003449,
+                            "total": 0.1589263739999751,
                             "count": 1,
-                            "self": 0.15991307900003449
+                            "self": 0.1589263739999751
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,58 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 10208,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.onnx",
-                "reward": 4.2727272727272725,
-                "creation_time": 1683279658.6516836,
+                "steps": 4976,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-4976.onnx",
+                "reward": 3.4545454545454546,
+                "creation_time": 1683279883.2266254,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-4976.pt"
+                ]
+            },
+            {
+                "steps": 9952,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-9952.onnx",
+                "reward": 2.4545454545454546,
+                "creation_time": 1683279895.269015,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-9952.pt"
+                ]
+            },
+            {
+                "steps": 14992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-14992.onnx",
+                "reward": 4.0,
+                "creation_time": 1683279907.0291903,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-14992.pt"
+                ]
+            },
+            {
+                "steps": 19992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-19992.onnx",
+                "reward": 6.363636363636363,
+                "creation_time": 1683279919.2386408,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-19992.pt"
+                ]
+            },
+            {
+                "steps": 20376,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-20376.onnx",
+                "reward": 6.363636363636363,
+                "creation_time": 1683279919.4465008,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-20376.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 10208,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 4.2727272727272725,
-            "creation_time": 1683279658.6516836,
+            "steps": 20376,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 6.363636363636363,
+            "creation_time": 1683279919.4465008,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-20376.pt"
             ]
         }
     },