First push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c564f2d782d61a49a2c104fcf9d62b0c5724e8b7e1830501fa4558bf3373666
+oid sha256:450b9fbce4b96940cc9dd2b15b1087246f4f8d6ff35240dba1dd448a7dace681
 size 1418184

Pyramids/{Pyramids-499878.onnx → Pyramids-1499984.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c17cbf77240216d8c812761864e839b25dcae50efb2c547edf88d73d74b1ee8
+oid sha256:77049c4d8eb1cd63ec7e235ada8923e5990c80f6c8586a415ede7d98a46059e5
 size 1418184

Pyramids/{Pyramids-499878.pt → Pyramids-1499984.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5da391aa2baca6b70affba443b2174ad874a53f37b72b53970af49e9d907d1
+oid sha256:ca799eafc39c821e4a18a8cfa5a0b4875c468ffb797bd84fbd0cb24423286f79
 size 8650990

Pyramids/{Pyramids-999971.onnx → Pyramids-1999881.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c564f2d782d61a49a2c104fcf9d62b0c5724e8b7e1830501fa4558bf3373666
+oid sha256:450b9fbce4b96940cc9dd2b15b1087246f4f8d6ff35240dba1dd448a7dace681
 size 1418184

Pyramids/{Pyramids-999971.pt → Pyramids-1999881.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6f0ea04ca3c48a0f362fb4b90fc0153c60057a8039c1f0d462bbbdae26aff4f
+oid sha256:c107b9948e0a00c4eb6f02876c5128e08beeb4c2aaae60d176771baca96e7ebd
 size 8650990

Pyramids/Pyramids-2000009.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:450b9fbce4b96940cc9dd2b15b1087246f4f8d6ff35240dba1dd448a7dace681
+size 1418184

Pyramids/Pyramids-2000009.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2abbc8b68e1c6f1849dd1f9fd5882b3720ae4482e7933e7d8e2e3a4d386787e2
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07564e2c7217f57ac9773078ac34f6988f522dc22d58e040069857d5bbab6f1a
+oid sha256:2abbc8b68e1c6f1849dd1f9fd5882b3720ae4482e7933e7d8e2e3a4d386787e2
 size 8650990

Pyramids/events.out.tfevents.1679762480.5716f2786667.37151.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057032a1c91415e282c1240b254d57e73bf5011aba5d0daeb0772246981a633a
+size 1375

Pyramids/events.out.tfevents.1679762511.5716f2786667.37350.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab44406796485512f818bd18c91bd0ca4165d9c50698c36566b825f3663f192
+size 296302

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "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}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "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": "Pyramids Training", "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": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "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}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "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": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -80,7 +80,7 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55450 [Flags] 2 [Guid] 1250661662 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55135 [Flags] 2 [Guid] 2536577225 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ 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  0.085 seconds
+- Completed reload, in  0.083 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)
@@ -68,7 +65,7 @@ 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: 0.739190 ms
+UnloadTime: 0.753176 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.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 5159 frames, [32.0 KB-64.0 KB]: 10657 frames, [64.0 KB-128.0 KB]: 2947 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1630 frames, [32.0 KB-64.0 KB]: 11142 frames, [64.0 KB-128.0 KB]: 5995 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
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18465 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 57 frames, [1.0 MB-2.0 MB]: 18711 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 10784
+  Peak main deferred allocation count 11210
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18763 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18767 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 31.0 MB
+      Peak Block count 2
+      Peak Allocated memory 25.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18764 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18768 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.1 MB
+      Peak Allocated memory 21.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18763 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18767 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18764 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18768 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18465 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 37 frames, [1.0 MB-2.0 MB]: 18731 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 18763 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18767 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -291,21 +288,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18764 frames
+      Peak usage frame count: [0-1.0 KB]: 18768 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]: 18764 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18768 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18764 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18768 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679761697110,"processId":24669,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679764986247,"processId":37370,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.3422085642814636,
-            "min": 0.3422085642814636,
-            "max": 1.4441567659378052,
+            "value": 0.19795969128608704,
+            "min": 0.17892177402973175,
+            "max": 0.39160123467445374,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 10173.17578125,
-            "min": 10173.17578125,
-            "max": 43809.94140625,
+            "value": 5948.29296875,
+            "min": 5373.37890625,
+            "max": 11716.708984375,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 274.85585585585585,
+            "min": 229.73643410852713,
+            "max": 333.5232558139535,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30509.0,
+            "min": 18321.0,
+            "max": 31268.0,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989932.0,
-            "min": 29952.0,
-            "max": 989932.0,
+            "value": 1979905.0,
+            "min": 1019947.0,
+            "max": 1979905.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989932.0,
-            "min": 29952.0,
-            "max": 989932.0,
+            "value": 1979905.0,
+            "min": 1019947.0,
+            "max": 1979905.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5808655023574829,
-            "min": -0.09019104391336441,
-            "max": 0.6199414134025574,
+            "value": 0.7205009460449219,
+            "min": 0.5460777878761292,
+            "max": 0.8055691719055176,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 163.22320556640625,
-            "min": -21.736042022705078,
-            "max": 179.16307067871094,
+            "value": 213.98878479003906,
+            "min": 99.93223571777344,
+            "max": 241.67074584960938,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.01583399437367916,
-            "min": 0.010855699889361858,
-            "max": 0.3748622238636017,
+            "value": 0.00788911059498787,
+            "min": -0.008039699867367744,
+            "max": 0.0302625373005867,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 4.449352264404297,
-            "min": 2.9310388565063477,
-            "max": 88.84234619140625,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0718149798811369,
-            "min": 0.0653742495231286,
-            "max": 0.07456588407202966,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.0054097183359165,
-            "min": 0.502867188713789,
-            "max": 1.0747806441253416,
+            "value": 2.3430659770965576,
+            "min": -2.347592353820801,
+            "max": 8.503772735595703,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.015425265024532564,
-            "min": 0.00013655981896167248,
-            "max": 0.017042330592974195,
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7254553426589285,
+            "min": 1.590122435546043,
+            "max": 1.768695984005928,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.2159537103434559,
-            "min": 0.0017752776465017423,
-            "max": 0.2556349588946129,
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 193.2509983778,
+            "min": 91.67799962311983,
+            "max": 228.1239980906248,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.465147511649999e-06,
-            "min": 7.465147511649999e-06,
-            "max": 0.00029515063018788575,
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7254553426589285,
+            "min": 1.590122435546043,
+            "max": 1.768695984005928,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010451206516309998,
-            "min": 0.00010451206516309998,
-            "max": 0.0035077148307618,
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 193.2509983778,
+            "min": 91.67799962311983,
+            "max": 228.1239980906248,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10248835,
-            "min": 0.10248835,
-            "max": 0.19838354285714285,
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.02336898377455197,
+            "min": 0.020513887662902533,
+            "max": 0.038077669581980444,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4348369,
-            "min": 1.3691136000000002,
-            "max": 2.5692382,
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.617326182749821,
+            "min": 2.132349496590905,
+            "max": 3.253328613616759,
             "count": 33
         },
-        "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025858616499999993,
-            "min": 0.00025858616499999993,
-            "max": 0.00983851593142857,
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06737127927325216,
+            "min": 0.06507654296327513,
+            "max": 0.07193620100900132,
             "count": 33
         },
-        "Pyramids.Policy.Beta.sum": {
-            "value": 0.003620206309999999,
-            "min": 0.003620206309999999,
-            "max": 0.11694689617999998,
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0105691890987825,
+            "min": 0.6003042566978063,
+            "max": 1.0488999902291276,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.01130596548318863,
-            "min": 0.01130596548318863,
-            "max": 0.5363889336585999,
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.014879609234410405,
+            "min": 0.012685737521516988,
+            "max": 0.016918260468039934,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.1582835167646408,
-            "min": 0.1582835167646408,
-            "max": 3.7547225952148438,
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.22319413851615608,
+            "min": 0.1246029937659235,
+            "max": 0.23685564655255908,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 318.4835164835165,
-            "min": 290.09183673469386,
-            "max": 999.0,
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 5.235348254916669e-06,
+            "min": 5.235348254916669e-06,
+            "max": 0.00014841658386115556,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28982.0,
-            "min": 15984.0,
-            "max": 32671.0,
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 7.853022382375003e-05,
+            "min": 7.853022382375003e-05,
+            "max": 0.0020361141712955497,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.659384423494339,
-            "min": -1.0000000521540642,
-            "max": 1.6690734497898696,
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10174508333333335,
+            "min": 0.10174508333333335,
+            "max": 0.1494721777777778,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 149.3445981144905,
-            "min": -32.000001668930054,
-            "max": 163.56919807940722,
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.5261762500000002,
+            "min": 1.3452496000000003,
+            "max": 2.17870445,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.659384423494339,
-            "min": -1.0000000521540642,
-            "max": 1.6690734497898696,
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.000184333825,
+            "min": 0.000184333825,
+            "max": 0.00495227056,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 149.3445981144905,
-            "min": -32.000001668930054,
-            "max": 163.56919807940722,
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.002765007375,
+            "min": 0.002765007375,
+            "max": 0.06795257455499999,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.03711442750969177,
-            "min": 0.03513040604860978,
-            "max": 10.622585339471698,
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.008348886854946613,
+            "min": 0.00799898337572813,
+            "max": 0.01131406333297491,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 3.3402984758722596,
-            "min": 3.3402984758722596,
-            "max": 169.96136543154716,
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.12523330748081207,
+            "min": 0.10182657092809677,
+            "max": 0.15106484293937683,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679759600",
+        "start_time_seconds": "1679762508",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --resume --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1679761697"
+        "end_time_seconds": "1679764986"
     },
-    "total": 2097.1515173280004,
+    "total": 2477.7979970040014,
     "count": 1,
-    "self": 0.5952326930000709,
+    "self": 0.47487297900261183,
     "children": {
         "run_training.setup": {
-            "total": 0.1115572680000696,
+            "total": 0.1086530889988353,
             "count": 1,
-            "self": 0.1115572680000696
+            "self": 0.1086530889988353
         },
         "TrainerController.start_learning": {
-            "total": 2096.4447273670003,
+            "total": 2477.214470936,
             "count": 1,
-            "self": 1.2643243429038193,
+            "self": 1.3786628168909374,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.959657988000799,
+                    "total": 6.55010490299901,
                     "count": 1,
-                    "self": 5.959657988000799
+                    "self": 6.55010490299901
                 },
                 "TrainerController.advance": {
-                    "total": 2089.075305752096,
-                    "count": 63829,
-                    "self": 1.3199584772410162,
+                    "total": 2469.1941361581084,
+                    "count": 65412,
+                    "self": 1.4882786821872287,
                     "children": {
                         "env_step": {
-                            "total": 1477.4242260999,
-                            "count": 63829,
-                            "self": 1374.6521468028313,
+                            "total": 1837.788205910132,
+                            "count": 65412,
+                            "self": 1730.137402586999,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 102.01152722504867,
-                                    "count": 63829,
-                                    "self": 4.460856669088571,
+                                    "total": 106.80889161200867,
+                                    "count": 65412,
+                                    "self": 4.579256114773671,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 97.5506705559601,
-                                            "count": 62546,
-                                            "self": 97.5506705559601
+                                            "total": 102.229635497235,
+                                            "count": 62560,
+                                            "self": 102.229635497235
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7605520720198911,
-                                    "count": 63829,
+                                    "total": 0.8419117111243395,
+                                    "count": 65412,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2092.2516991530774,
-                                            "count": 63829,
+                                            "total": 2471.83919368398,
+                                            "count": 65412,
                                             "is_parallel": true,
-                                            "self": 828.0267487680876,
+                                            "self": 858.5424031159691,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0018746629993984243,
+                                                            "total": 0.0016750790000514826,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005044190011176397,
+                                                            "self": 0.0005376200006139698,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013702439982807846,
+                                                                    "total": 0.0011374589994375128,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013702439982807846
+                                                                    "self": 0.0011374589994375128
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04709258500042779,
+                                                            "total": 0.07919898999898578,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004982470009053941,
+                                                            "self": 0.0004944439988321392,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00043726300009439,
+                                                                    "total": 0.0004383019986562431,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00043726300009439
+                                                                    "self": 0.0004383019986562431
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04441314900032012,
+                                                                    "total": 0.07669147300111945,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04441314900032012
+                                                                    "self": 0.07669147300111945
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001743925999107887,
+                                                                    "total": 0.0015747710003779503,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004175379999651341,
+                                                                    "self": 0.00037540799712587614,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001326387999142753,
+                                                                            "total": 0.0011993630032520741,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001326387999142753
+                                                                            "self": 0.0011993630032520741
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1264.2249503849898,
-                                                    "count": 63828,
+                                                    "total": 1613.2967905680107,
+                                                    "count": 65411,
                                                     "is_parallel": true,
-                                                    "self": 29.959005575045012,
+                                                    "self": 30.840027512387678,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 21.734907273053068,
-                                                            "count": 63828,
+                                                            "total": 22.224878790815637,
+                                                            "count": 65411,
                                                             "is_parallel": true,
-                                                            "self": 21.734907273053068
+                                                            "self": 22.224878790815637
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1124.3263568840184,
-                                                            "count": 63828,
+                                                            "total": 1468.603954711847,
+                                                            "count": 65411,
                                                             "is_parallel": true,
-                                                            "self": 1124.3263568840184
+                                                            "self": 1468.603954711847
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 88.20468065287332,
-                                                            "count": 63828,
+                                                            "total": 91.62792955296027,
+                                                            "count": 65411,
                                                             "is_parallel": true,
-                                                            "self": 18.20092035689504,
+                                                            "self": 19.466922851213894,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 70.00376029597828,
-                                                                    "count": 510624,
+                                                                    "total": 72.16100670174637,
+                                                                    "count": 523288,
                                                                     "is_parallel": true,
-                                                                    "self": 70.00376029597828
+                                                                    "self": 72.16100670174637
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 610.3311211749551,
-                            "count": 63829,
-                            "self": 2.387781350721525,
+                            "total": 629.9176515657891,
+                            "count": 65412,
+                            "self": 2.7014179858852003,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 115.11368088023664,
-                                    "count": 63829,
-                                    "self": 114.80844624323709,
+                                    "total": 123.35763384293205,
+                                    "count": 65412,
+                                    "self": 123.14899652393251,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.30523463699955755,
+                                            "total": 0.20863731899953564,
                                             "count": 2,
-                                            "self": 0.30523463699955755
+                                            "self": 0.20863731899953564
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 492.82965894399695,
-                                    "count": 448,
-                                    "self": 311.8260051449515,
+                                    "total": 503.8585997369719,
+                                    "count": 473,
+                                    "self": 319.8509355107999,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 181.00365379904542,
-                                            "count": 22857,
-                                            "self": 181.00365379904542
+                                            "total": 184.00766422617198,
+                                            "count": 22749,
+                                            "self": 184.00766422617198
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2599994079209864e-06,
+                    "total": 8.800016075838357e-07,
                     "count": 1,
-                    "self": 1.2599994079209864e-06
+                    "self": 8.800016075838357e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.14543802400021377,
+                    "total": 0.09156617799999367,
                     "count": 1,
-                    "self": 0.0018555160004325444,
+                    "self": 0.0017570099989825394,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.14358250799978123,
+                            "total": 0.08980916800101113,
                             "count": 1,
-                            "self": 0.14358250799978123
+                            "self": 0.08980916800101113
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499878,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499878.onnx",
-                "reward": 1.7139999568462372,
-                "creation_time": 1679760560.1931126,
+                "steps": 1000034,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000034.onnx",
+                "reward": 1.794400018453598,
+                "creation_time": 1679761696.5578232,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499878.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000034.pt"
                 ]
             },
             {
-                "steps": 999971,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999971.onnx",
-                "reward": 1.790500033646822,
-                "creation_time": 1679761696.4028628,
+                "steps": 1000034,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000034.onnx",
+                "reward": null,
+                "creation_time": 1679762483.3187692,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999971.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000034.pt"
                 ]
             },
             {
-                "steps": 1000034,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000034.onnx",
-                "reward": 1.794400018453598,
-                "creation_time": 1679761696.5578232,
+                "steps": 1499984,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499984.onnx",
+                "reward": 1.82300000389417,
+                "creation_time": 1679763746.5320272,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000034.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499984.pt"
+                ]
+            },
+            {
+                "steps": 1999881,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999881.onnx",
+                "reward": 1.7903332859277725,
+                "creation_time": 1679764985.7349083,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999881.pt"
+                ]
+            },
+            {
+                "steps": 2000009,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000009.onnx",
+                "reward": 1.7903332859277725,
+                "creation_time": 1679764985.836965,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2000009.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000034,
+            "steps": 2000009,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.794400018453598,
-            "creation_time": 1679761696.5578232,
+            "reward": 1.7903332859277725,
+            "creation_time": 1679764985.836965,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000034.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2000009.pt"
             ]
         }
     },