change learning rate and num layers

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4107877b79c5998ddfb46dc33376abffeba901dd91b0d9d813fedb3516812231
-size 2469240
+oid sha256:18b20e3874c9c2397cfca6cd6bde111e235fda914ae90cfcbfe4f51ca4264067
+size 1418184

Pyramids/Pyramids-1000061.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4107877b79c5998ddfb46dc33376abffeba901dd91b0d9d813fedb3516812231
-size 2469240

Pyramids/Pyramids-1000061.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1e8f718d3e6d7d4b21b7adb519c9fd1bb87d14152115a75343a6fabf0d56f3c1
-size 14958666

Pyramids/Pyramids-1000065.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:009092ee6b032a4a1ff9ce2d7534b6a0c3456a33b3a26759c8ada1fe6dc1be36
-size 8650990

Pyramids/{Pyramids-499908.onnx → Pyramids-1000105.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f11720e368ab4d11b5bf902992d3af3663e1c04d378fecbd8db4e44dac39316
+oid sha256:18b20e3874c9c2397cfca6cd6bde111e235fda914ae90cfcbfe4f51ca4264067
 size 1418184

Pyramids/{Pyramids-166144.pt → Pyramids-1000105.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18707db9c3a7339ec3ca6cdcd4b59669a11c72ece0f03fac39bc5d3984278176
+oid sha256:db4682505a273ea93432cf3b762843269ad0ef60c565f6b65112d844c24ee76f
 size 8650990

Pyramids/{Pyramids-166144.onnx → Pyramids-499941.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8929c8108967e18aff344642a61561a37c50124ef547b177805789d475dc3ec4
+oid sha256:fe12e5b5b00302481971fe6a2d87c8564490c60d9a731985570c477758d8c263
 size 1418184

Pyramids/{Pyramids-499908.pt → Pyramids-499941.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337ff33885764cbea812a1d611c86e034db02fc660d80d465a0c03c02bf84ce5
+oid sha256:1efb47e15a6a693e3c8c2bdaf48074935f5d5ebd1bce00ff20a2ed01eca26058
 size 8650990

Pyramids/Pyramids-499973.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65c083d956560d41d6601fbbf53c7184d37408c10d90985c8918d6e922ae44af
-size 2469240

Pyramids/Pyramids-499973.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:71073ea25d1ef0ac4daf6b26d71356583001fd47b2182931649974960632a214
-size 14958666

Pyramids/Pyramids-999933.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4107877b79c5998ddfb46dc33376abffeba901dd91b0d9d813fedb3516812231
-size 2469240

Pyramids/Pyramids-999933.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c185bd003a171f4e31d5c2882b1ac9b0bc14405f0b761a1add1b5cb0929e2188
-size 14958666

Pyramids/Pyramids-999937.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3e1cb3fda04337a74fa694903bcfd95f7258c4f04770e4bd5189d15b85b1a715
-size 1418184

Pyramids/{Pyramids-1000065.onnx → Pyramids-999977.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1cb3fda04337a74fa694903bcfd95f7258c4f04770e4bd5189d15b85b1a715
+oid sha256:18b20e3874c9c2397cfca6cd6bde111e235fda914ae90cfcbfe4f51ca4264067
 size 1418184

Pyramids/{Pyramids-999937.pt → Pyramids-999977.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744124e8dacf04f5ddb4971b4931c5febb2fb7d5ee42ec02521ca3244708cf56
+oid sha256:a8d37537af1aeda89a858ccd7dae5561935ec3ec3a0b22aac80a8d8ba977e9eb
 size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e8f718d3e6d7d4b21b7adb519c9fd1bb87d14152115a75343a6fabf0d56f3c1
-size 14958666
+oid sha256:db4682505a273ea93432cf3b762843269ad0ef60c565f6b65112d844c24ee76f
+size 8650990

Pyramids/{events.out.tfevents.1679910674.efb1629e622b.36958.0 → events.out.tfevents.1679923257.3a4040274475.3942.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd7c3692a6a3cf1593c4c09e501c12dd3e912566f7ba081f639749992dfbddc
-size 304258
+oid sha256:8f1971fe88a74c6b06111b1e0f9050d8ed52b59d959f685cdf93fd3a1c179bd3
+size 314572

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.001, "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": 3, "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": 0.001, "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": true, "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": 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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.001
+      learning_rate: 0.0003
       beta: 0.01
       epsilon: 0.2
       lambd: 0.95
@@ -18,7 +18,7 @@ behaviors:
     network_settings:
       normalize: false
       hidden_units: 512
-      num_layers: 3
+      num_layers: 2
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -46,7 +46,7 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-        learning_rate: 0.001
+        learning_rate: 0.0001
         encoding_size: null
     init_path: null
     keep_checkpoints: 5

run_logs/Player-0.log

@@ -1,9 +1,12 @@
 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] 55245 [Flags] 2 [Guid] 2370357202 [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] 55480 [Flags] 2 [Guid] 4097042660 [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
@@ -33,7 +36,7 @@ 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  0.088 seconds
+- Completed reload, in  0.093 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)
@@ -65,7 +68,7 @@ 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: 0.879922 ms
+UnloadTime: 0.856600 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.
@@ -73,7 +76,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 12105 frames, [32.0 KB-64.0 KB]: 5266 frames, [64.0 KB-128.0 KB]: 1397 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1623 frames, [32.0 KB-64.0 KB]: 12917 frames, [64.0 KB-128.0 KB]: 4230 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
@@ -123,12 +126,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -204,28 +207,28 @@ 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]: 18470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12989
+  Peak main deferred allocation count 12723
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18768 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.6 MB
+      Peak Allocated memory 30.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.4 MB
+      Peak Allocated memory 22.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,13 +257,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 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]: 18769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,13 +275,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 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]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18770 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
@@ -290,19 +293,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18769 frames
+      Peak usage frame count: [0-1.0 KB]: 18771 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]: 18769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18771 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]: 18769 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18771 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -311,4 +314,4 @@ 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":1679912626586,"processId":36976,"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":1679925502357,"processId":3962,"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": 0.33155301213264465,
-            "min": 0.29641273617744446,
-            "max": 1.4473973512649536,
+            "value": 0.2865666449069977,
+            "min": 0.2865666449069977,
+            "max": 1.418717622756958,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 9845.7978515625,
-            "min": 8878.154296875,
-            "max": 43908.24609375,
+            "value": 8610.7548828125,
+            "min": 8610.7548828125,
+            "max": 43038.21875,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989878.0,
-            "min": 29952.0,
-            "max": 989878.0,
+            "value": 989999.0,
+            "min": 29890.0,
+            "max": 989999.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989878.0,
-            "min": 29952.0,
-            "max": 989878.0,
+            "value": 989999.0,
+            "min": 29890.0,
+            "max": 989999.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.0003719172964338213,
-            "min": -0.10535166412591934,
-            "max": 0.06039966270327568,
+            "value": 0.7499698996543884,
+            "min": -0.09243645519018173,
+            "max": 0.7499698996543884,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.09037590026855469,
-            "min": -25.389751434326172,
-            "max": 14.314720153808594,
+            "value": 224.24099731445312,
+            "min": -22.184749603271484,
+            "max": 224.24099731445312,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.0050484007224440575,
-            "min": 0.0027310100849717855,
-            "max": 0.2063242644071579,
+            "value": 0.010645143687725067,
+            "min": -0.007272213231772184,
+            "max": 0.3172692060470581,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.2267613410949707,
-            "min": 0.6609044671058655,
-            "max": 48.89884948730469,
+            "value": 3.1828980445861816,
+            "min": -2.0507640838623047,
+            "max": 75.19280242919922,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07010793154030392,
-            "min": 0.06523566317518081,
-            "max": 0.1376351349175262,
+            "value": 0.07069740374156805,
+            "min": 0.06517258709855346,
+            "max": 0.07235309784463109,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.981511041564255,
-            "min": 0.49365625917712824,
-            "max": 1.9268918888453666,
+            "value": 0.9897636523819527,
+            "min": 0.5064716849124177,
+            "max": 1.0637572742028474,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0038961110385676463,
-            "min": 1.5120520453554468e-05,
-            "max": 0.005290081879582984,
+            "value": 0.01665427011210427,
+            "min": 0.00046069519045440404,
+            "max": 0.017761774997912344,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.05454555453994705,
-            "min": 0.00012096416362843574,
-            "max": 0.05454555453994705,
+            "value": 0.23315978156945977,
+            "min": 0.0041462567140896365,
+            "max": 0.24866484997077282,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.4250240432128572e-05,
-            "min": 2.4250240432128572e-05,
-            "max": 0.0009838354301878855,
+            "value": 7.571668904714283e-06,
+            "min": 7.571668904714283e-06,
+            "max": 0.0002952355730167143,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0003395033660498,
-            "min": 0.0003395033660498,
-            "max": 0.0104684242531576,
+            "value": 0.00010600336466599996,
+            "min": 0.00010600336466599996,
+            "max": 0.0036336640887787005,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1024250142857143,
-            "min": 0.1024250142857143,
-            "max": 0.19838354285714285,
+            "value": 0.10252385714285715,
+            "min": 0.10252385714285715,
+            "max": 0.1984118571428571,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4339502000000002,
-            "min": 1.3691136000000002,
-            "max": 2.4824814,
+            "value": 1.435334,
+            "min": 1.3888829999999999,
+            "max": 2.6112213000000004,
             "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002522589271428572,
-            "min": 0.0002522589271428572,
-            "max": 0.00983851593142857,
+            "value": 0.00026213332857142853,
+            "min": 0.00026213332857142853,
+            "max": 0.009841344528571428,
             "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.003531624980000001,
-            "min": 0.003531624980000001,
-            "max": 0.10470955576,
+            "value": 0.0036698665999999993,
+            "min": 0.0036698665999999993,
+            "max": 0.12114100786999998,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.004714164882898331,
-            "min": 0.004437954630702734,
-            "max": 0.08432412892580032,
+            "value": 0.008870440535247326,
+            "min": 0.008870440535247326,
+            "max": 0.43551698327064514,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.06599830836057663,
-            "min": 0.062131367623806,
-            "max": 0.5902689099311829,
+            "value": 0.12418617308139801,
+            "min": 0.12418617308139801,
+            "max": 3.048618793487549,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 879.8857142857142,
-            "min": 879.8857142857142,
+            "value": 233.19230769230768,
+            "min": 233.19230769230768,
             "max": 999.0,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30796.0,
-            "min": 15984.0,
-            "max": 32788.0,
+            "value": 30315.0,
+            "min": 16689.0,
+            "max": 33397.0,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.3660400448100907,
-            "min": -1.0000000521540642,
-            "max": -0.3660400448100907,
+            "value": 1.751418452652601,
+            "min": -0.9999742455059483,
+            "max": 1.751418452652601,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -12.811401568353176,
-            "min": -32.000001668930054,
-            "max": -12.811401568353176,
+            "value": 227.68439884483814,
+            "min": -31.998401656746864,
+            "max": 227.68439884483814,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.3660400448100907,
-            "min": -1.0000000521540642,
-            "max": -0.3660400448100907,
+            "value": 1.751418452652601,
+            "min": -0.9999742455059483,
+            "max": 1.751418452652601,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -12.811401568353176,
-            "min": -32.000001668930054,
-            "max": -12.811401568353176,
+            "value": 227.68439884483814,
+            "min": -31.998401656746864,
+            "max": 227.68439884483814,
             "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.04601131717354292,
-            "min": 0.04601131717354292,
-            "max": 5.092708854121156,
+            "value": 0.021346968652841705,
+            "min": 0.021346968652841705,
+            "max": 8.696528516271535,
             "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 1.6103961010740022,
-            "min": 1.527434264688054,
-            "max": 81.4833416659385,
+            "value": 2.775105924869422,
+            "min": 2.7179872871784028,
+            "max": 147.8409847766161,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,7 +184,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679910671",
+        "start_time_seconds": "1679923250",
         "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 --force",
         "mlagents_version": "0.31.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1679912626"
+        "end_time_seconds": "1679925502"
     },
-    "total": 1955.3765004980014,
+    "total": 2251.434469328,
     "count": 1,
-    "self": 0.47612167700026475,
+    "self": 0.44148582399975567,
     "children": {
         "run_training.setup": {
-            "total": 0.11152717100048903,
+            "total": 0.12052986699995927,
             "count": 1,
-            "self": 0.11152717100048903
+            "self": 0.12052986699995927
         },
         "TrainerController.start_learning": {
-            "total": 1954.7888516500007,
+            "total": 2250.872453637,
             "count": 1,
-            "self": 1.3155119283164822,
+            "self": 1.3635675539885597,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 7.115794675999496,
+                    "total": 10.481035571000007,
                     "count": 1,
-                    "self": 7.115794675999496
+                    "self": 10.481035571000007
                 },
                 "TrainerController.advance": {
-                    "total": 1946.2269501136852,
-                    "count": 63109,
-                    "self": 1.3804438265651697,
+                    "total": 2238.937677368011,
+                    "count": 64471,
+                    "self": 1.4948823420286317,
                     "children": {
                         "env_step": {
-                            "total": 1295.7710330421578,
-                            "count": 63109,
-                            "self": 1183.6033093427886,
+                            "total": 1615.0481244640066,
+                            "count": 64471,
+                            "self": 1506.4905466610016,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 111.35507200813845,
-                                    "count": 63109,
-                                    "self": 4.615316210974925,
+                                    "total": 107.7018033789659,
+                                    "count": 64471,
+                                    "self": 4.8431241869801624,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 106.73975579716353,
-                                            "count": 62563,
-                                            "self": 106.73975579716353
+                                            "total": 102.85867919198574,
+                                            "count": 62569,
+                                            "self": 102.85867919198574
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8126516912307125,
-                                    "count": 63109,
+                                    "total": 0.8557744240389411,
+                                    "count": 64471,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1950.327473006173,
-                                            "count": 63109,
+                                            "total": 2245.647674626964,
+                                            "count": 64471,
                                             "is_parallel": true,
-                                            "self": 878.4651561174651,
+                                            "self": 858.1431635469739,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0018653160004760139,
+                                                            "total": 0.006129108999971322,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005306500006554415,
+                                                            "self": 0.004679749999809246,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013346659998205723,
+                                                                    "total": 0.001449359000162076,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013346659998205723
+                                                                    "self": 0.001449359000162076
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.08514848999948299,
+                                                            "total": 0.07743932799996855,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005558450011449168,
+                                                            "self": 0.0005306780000182698,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004275999999663327,
+                                                                    "total": 0.0004938449999372096,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004275999999663327
+                                                                    "self": 0.0004938449999372096
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.08236286799910886,
+                                                                    "total": 0.07461291899994649,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.08236286799910886
+                                                                    "self": 0.07461291899994649
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018021769992628833,
+                                                                    "total": 0.0018018860000665882,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003738120030902792,
+                                                                    "self": 0.0003843609998739339,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014283649961726042,
+                                                                            "total": 0.0014175250001926543,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014283649961726042
+                                                                            "self": 0.0014175250001926543
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1071.862316888708,
-                                                    "count": 63108,
+                                                    "total": 1387.5045110799902,
+                                                    "count": 64470,
                                                     "is_parallel": true,
-                                                    "self": 31.438335106984596,
+                                                    "self": 31.55784679892804,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.920386829038762,
-                                                            "count": 63108,
+                                                            "total": 23.95438901101238,
+                                                            "count": 64470,
                                                             "is_parallel": true,
-                                                            "self": 22.920386829038762
+                                                            "self": 23.95438901101238
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 924.969774630048,
-                                                            "count": 63108,
+                                                            "total": 1236.1973490219711,
+                                                            "count": 64470,
                                                             "is_parallel": true,
-                                                            "self": 924.969774630048
+                                                            "self": 1236.1973490219711
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 92.53382032263653,
-                                                            "count": 63108,
+                                                            "total": 95.79492624807847,
+                                                            "count": 64470,
                                                             "is_parallel": true,
-                                                            "self": 19.286263672998757,
+                                                            "self": 20.733071304069085,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 73.24755664963777,
-                                                                    "count": 504864,
+                                                                    "total": 75.06185494400938,
+                                                                    "count": 515760,
                                                                     "is_parallel": true,
-                                                                    "self": 73.24755664963777
+                                                                    "self": 75.06185494400938
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 649.0754732449623,
-                            "count": 63109,
-                            "self": 2.3674188757177035,
+                            "total": 622.3946705619757,
+                            "count": 64471,
+                            "self": 2.632667645995525,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 118.98177979024149,
-                                    "count": 63109,
-                                    "self": 118.70513996824229,
+                                    "total": 123.44340726898179,
+                                    "count": 64471,
+                                    "self": 123.16643085698172,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.276639821999197,
+                                            "total": 0.2769764120000673,
                                             "count": 2,
-                                            "self": 0.276639821999197
+                                            "self": 0.2769764120000673
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 527.7262745790031,
-                                    "count": 435,
-                                    "self": 327.2420792710873,
+                                    "total": 496.31859564699835,
+                                    "count": 454,
+                                    "self": 316.60305228302036,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 200.4841953079158,
-                                            "count": 22746,
-                                            "self": 200.4841953079158
+                                            "total": 179.715543363978,
+                                            "count": 22812,
+                                            "self": 179.715543363978
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3250009942566976e-06,
+                    "total": 1.0090002433571499e-06,
                     "count": 1,
-                    "self": 1.3250009942566976e-06
+                    "self": 1.0090002433571499e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.13059360699844547,
+                    "total": 0.09017213500010257,
                     "count": 1,
-                    "self": 0.0028494499983935384,
+                    "self": 0.0013485819999914384,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12774415700005193,
+                            "total": 0.08882355300011113,
                             "count": 1,
-                            "self": 0.12774415700005193
+                            "self": 0.08882355300011113
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499973,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499973.onnx",
+                "steps": 499941,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499941.onnx",
                 "reward": null,
-                "creation_time": 1679911662.639504,
+                "creation_time": 1679924285.2919362,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499973.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499941.pt"
                 ]
             },
             {
-                "steps": 999933,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999933.onnx",
-                "reward": 1.6819999516010284,
-                "creation_time": 1679912626.0189764,
+                "steps": 999977,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999977.onnx",
+                "reward": 1.2834999871750672,
+                "creation_time": 1679925501.8463953,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999933.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999977.pt"
                 ]
             },
             {
-                "steps": 1000061,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000061.onnx",
-                "reward": 1.6819999516010284,
-                "creation_time": 1679912626.157252,
+                "steps": 1000105,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000105.onnx",
+                "reward": 1.2834999871750672,
+                "creation_time": 1679925501.9458117,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000061.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000105.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000061,
+            "steps": 1000105,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.6819999516010284,
-            "creation_time": 1679912626.157252,
+            "reward": 1.2834999871750672,
+            "creation_time": 1679925501.9458117,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000061.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000105.pt"
             ]
         }
     },