further training without RND

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6792d5d8033b6381f518c6911d61b8be518a8b554c117c4afb4e8282dc90848b
+oid sha256:21cd29ad37a37c2ba368754f09107d606efd009e2bb5cafbe2ef492e0a7b0aee
 size 1420238

Pyramids/Pyramids-1499878.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82ebc0a9f8484e5059c1b4531874a9ea9c232ff53b218f36d700bfb82c38111
+size 1420238

Pyramids/Pyramids-1499878.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b0bc7cac0c7bf30340533d0b38bd96faee2b57eec5d1def900ba0ff267f7db
+size 10003291

Pyramids/Pyramids-1999911.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21cd29ad37a37c2ba368754f09107d606efd009e2bb5cafbe2ef492e0a7b0aee
+size 1420238

Pyramids/Pyramids-1999911.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18ab6e51b45b66502cfb488d9a5e4ae0e83df3c3dd06fed0da2c7964db938c0
+size 10003291

Pyramids/Pyramids-2000039.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21cd29ad37a37c2ba368754f09107d606efd009e2bb5cafbe2ef492e0a7b0aee
+size 1420238

Pyramids/Pyramids-2000039.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7efd4a6c0f6c28517cdf44bd70fc6de757f0200b278ef6d63167d8c341bf42b6
+size 10003291

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1553bc11a49b1689288f45bd3751df3a9b726e4c8cc0b1cba63c2e4132a6fa00
-size 8655157
+oid sha256:643cbabb3b5e6ec150f0a579469c2e3b9e3918b81565397ba00f2591363f1a5f
+size 10002805

Pyramids/events.out.tfevents.1763077444.13dac218fcd6.6933.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab263b686885cfabd702a20efe4e7309575343348a0ddee269e36480e39340a
+size 308918

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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.02, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "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

@@ -35,23 +35,23 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-      rnd:
+      curiosity:
         gamma: 0.99
-        strength: 0.01
+        strength: 0.02
         network_settings:
           normalize: false
-          hidden_units: 64
-          num_layers: 3
+          hidden_units: 256
+          num_layers: 2
           vis_encode_type: simple
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-        learning_rate: 0.0001
+        learning_rate: 0.0003
         encoding_size: null
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -79,10 +79,10 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  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] 55339 [Flags] 2 [Guid] 487889638 [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] 55172 [Flags] 2 [Guid] 2975614326 [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:2664:(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  0.089 seconds
+- Completed reload, in  0.087 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: 0.891568 ms
+UnloadTime: 0.783284 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.
@@ -81,7 +78,7 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 6359 frames, [32.0 KB-64.0 KB]: 10011 frames, [64.0 KB-128.0 KB]: 2394 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2819 frames, [32.0 KB-64.0 KB]: 10021 frames, [64.0 KB-128.0 KB]: 5929 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]: 18466 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 46 frames, [1.0 MB-2.0 MB]: 18724 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 12338
+  Peak main deferred allocation count 12856
     [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]: 18764 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18769 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 31.0 MB
+      Peak Block count 2
+      Peak Allocated memory 24.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18765 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18770 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.1 MB
+      Peak Allocated memory 23.2 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]: 18764 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18769 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]: 18765 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18770 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]: 18466 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 55 frames, [1.0 MB-2.0 MB]: 18715 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]: 18764 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18769 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]: 18765 frames
+      Peak usage frame count: [0-1.0 KB]: 18770 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]: 18765 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18770 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]: 18765 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18770 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":1763069410340,"processId":20907,"allocatedMemory":1970545,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":11015},{"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":1763079927130,"processId":6953,"allocatedMemory":1970545,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":11015},{"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 +2,183 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.5202416181564331,
-            "min": 0.5202416181564331,
-            "max": 1.3724439144134521,
+            "value": 0.21229027211666107,
+            "min": 0.2117043137550354,
+            "max": 0.45928406715393066,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 15598.923828125,
-            "min": 15598.923828125,
-            "max": 41634.45703125,
+            "value": 6348.328125,
+            "min": 6348.328125,
+            "max": 13844.6591796875,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 224.6124031007752,
+            "min": 224.6124031007752,
+            "max": 460.24285714285713,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28975.0,
+            "min": 15241.0,
+            "max": 33246.0,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989954.0,
-            "min": 29952.0,
-            "max": 989954.0,
+            "value": 1979990.0,
+            "min": 1019930.0,
+            "max": 1979990.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989954.0,
-            "min": 29952.0,
-            "max": 989954.0,
+            "value": 1979990.0,
+            "min": 1019930.0,
+            "max": 1979990.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.39459800720214844,
-            "min": -0.07974208146333694,
-            "max": 0.4636046588420868,
+            "value": 0.7928503751754761,
+            "min": 0.4259541630744934,
+            "max": 0.7928503751754761,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 104.96306610107422,
-            "min": -19.138099670410156,
-            "max": 124.70965576171875,
+            "value": 236.2694091796875,
+            "min": 74.54197692871094,
+            "max": 236.2694091796875,
             "count": 33
         },
-        "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.16277073323726654,
-            "min": -0.16277073323726654,
-            "max": 0.5576831102371216,
+        "Pyramids.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.08150467276573181,
+            "min": 0.07122068107128143,
+            "max": 0.9572137594223022,
             "count": 33
         },
-        "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -43.29701614379883,
-            "min": -43.29701614379883,
-            "max": 132.1708984375,
+        "Pyramids.Policy.CuriosityValueEstimate.sum": {
+            "value": 24.288393020629883,
+            "min": 20.867658615112305,
+            "max": 250.8644256591797,
             "count": 33
         },
-        "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06697754384367725,
-            "min": 0.06493085783343606,
-            "max": 0.07217698134674302,
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7598759609945984,
+            "min": 1.3477056824735232,
+            "max": 1.7610719833374024,
             "count": 33
         },
-        "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9376856138114816,
-            "min": 0.4734105893886439,
-            "max": 1.068348917038141,
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 227.0239989683032,
+            "min": 70.8859993070364,
+            "max": 227.0239989683032,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.022717639452561604,
-            "min": 0.0004143780640323199,
-            "max": 0.022717639452561604,
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7598759609945984,
+            "min": 1.3477056824735232,
+            "max": 1.7610719833374024,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.31804695233586244,
-            "min": 0.0053869148324201584,
-            "max": 0.31804695233586244,
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 227.0239989683032,
+            "min": 70.8859993070364,
+            "max": 227.0239989683032,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.690683150757139e-06,
-            "min": 7.690683150757139e-06,
-            "max": 0.00029515063018788575,
+        "Pyramids.Policy.CuriosityReward.mean": {
+            "value": 0.1361309675361723,
+            "min": 0.13419253882020712,
+            "max": 8.166471420678981,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010766956411059995,
-            "min": 0.00010766956411059995,
-            "max": 0.0036328843890386,
+        "Pyramids.Policy.CuriosityReward.sum": {
+            "value": 17.560894812166225,
+            "min": 16.77406735252589,
+            "max": 351.1582710891962,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10256352857142856,
-            "min": 0.10256352857142856,
-            "max": 0.19838354285714285,
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06777143211054083,
+            "min": 0.06455791987166011,
+            "max": 0.0726872975951881,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4358893999999998,
-            "min": 1.3886848,
-            "max": 2.6109614000000003,
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9488000495475716,
+            "min": 0.6456835290203647,
+            "max": 1.0768589311046524,
             "count": 33
         },
-        "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026609650428571416,
-            "min": 0.00026609650428571416,
-            "max": 0.00983851593142857,
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015221940508733193,
+            "min": 0.012300340361737955,
+            "max": 0.03165379860891133,
             "count": 33
         },
-        "Pyramids.Policy.Beta.sum": {
-            "value": 0.003725351059999998,
-            "min": 0.003725351059999998,
-            "max": 0.12111504386000001,
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21310716712226468,
+            "min": 0.17220476506433138,
+            "max": 0.28488418748020194,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.015624910593032837,
-            "min": 0.015384450554847717,
-            "max": 0.6450778245925903,
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 5.150198283299999e-06,
+            "min": 5.150198283299999e-06,
+            "max": 0.0001484157338614389,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.21874874830245972,
-            "min": 0.21538230776786804,
-            "max": 4.515544891357422,
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 7.210277596619998e-05,
+            "min": 7.210277596619998e-05,
+            "max": 0.0020357597214137,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 446.92753623188406,
-            "min": 390.68831168831167,
-            "max": 999.0,
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10171670000000001,
+            "min": 0.10171670000000001,
+            "max": 0.14947189444444448,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30838.0,
-            "min": 15984.0,
-            "max": 35207.0,
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4240338000000001,
+            "min": 1.3452470500000002,
+            "max": 2.1785862999999996,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.4435088024200762,
-            "min": -1.0000000521540642,
-            "max": 1.4534259513988124,
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00018149832999999997,
+            "min": 0.00018149832999999997,
+            "max": 0.004952242254999999,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 98.15859856456518,
-            "min": -29.83060158789158,
-            "max": 111.91379825770855,
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0025409766199999996,
+            "min": 0.0025409766199999996,
+            "max": 0.06794077137,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.4435088024200762,
-            "min": -1.0000000521540642,
-            "max": 1.4534259513988124,
+        "Pyramids.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.02933511003253183,
+            "min": 0.026961324524341357,
+            "max": 3.1736685284585864,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 98.15859856456518,
-            "min": -29.83060158789158,
-            "max": 111.91379825770855,
+        "Pyramids.Losses.CuriosityForwardLoss.sum": {
+            "value": 0.4106915404554456,
+            "min": 0.40441986786512035,
+            "max": 28.56301675612728,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.070481658763396,
-            "min": 0.06648051149858912,
-            "max": 13.520335402339697,
+        "Pyramids.Losses.CuriosityInverseLoss.mean": {
+            "value": 0.029640588287293212,
+            "min": 0.029640588287293212,
+            "max": 0.3566509762571918,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 4.792752795910928,
-            "min": 4.666952816522098,
-            "max": 216.32536643743515,
+        "Pyramids.Losses.CuriosityInverseLoss.sum": {
+            "value": 0.414968236022105,
+            "min": 0.414968236022105,
+            "max": 3.209858786314726,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +196,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1763067100",
+        "start_time_seconds": "1763077443",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "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/Pyramids.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids-Training --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1763069410"
+        "end_time_seconds": "1763079927"
     },
-    "total": 2309.863566885,
+    "total": 2483.756702148,
     "count": 1,
-    "self": 0.5260048090003693,
+    "self": 0.4796895609997591,
     "children": {
         "run_training.setup": {
-            "total": 0.023349570999926073,
+            "total": 0.023456103000171424,
             "count": 1,
-            "self": 0.023349570999926073
+            "self": 0.023456103000171424
         },
         "TrainerController.start_learning": {
-            "total": 2309.314212505,
+            "total": 2483.253556484,
             "count": 1,
-            "self": 1.5412430310107084,
+            "self": 1.293926397985615,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.754416757999934,
+                    "total": 2.227432239000109,
                     "count": 1,
-                    "self": 1.754416757999934
+                    "self": 2.227432239000109
                 },
                 "TrainerController.advance": {
-                    "total": 2305.96594720099,
-                    "count": 63547,
-                    "self": 1.5190941318269324,
+                    "total": 2479.644286051014,
+                    "count": 65357,
+                    "self": 1.3399506230234692,
                     "children": {
                         "env_step": {
-                            "total": 1511.2713327452257,
-                            "count": 63547,
-                            "self": 1400.0459070052948,
+                            "total": 1728.4216181530269,
+                            "count": 65357,
+                            "self": 1585.745305189071,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 110.33114001783451,
-                                    "count": 63547,
-                                    "self": 4.542140675869632,
+                                    "total": 141.89125865498022,
+                                    "count": 65357,
+                                    "self": 4.438709465026932,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 105.78899934196488,
-                                            "count": 62548,
-                                            "self": 105.78899934196488
+                                            "total": 137.4525491899533,
+                                            "count": 62564,
+                                            "self": 137.4525491899533
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.894285722096356,
-                                    "count": 63547,
+                                    "total": 0.7850543089757593,
+                                    "count": 65357,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2302.960189066909,
-                                            "count": 63547,
+                                            "total": 2477.0554484660784,
+                                            "count": 65357,
                                             "is_parallel": true,
-                                            "self": 1024.6882308479871,
+                                            "self": 1005.134249613156,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0017828279997047503,
+                                                            "total": 0.0017356599998947786,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005650869998135022,
+                                                            "self": 0.0005625610001516179,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001217740999891248,
+                                                                    "total": 0.0011730989997431607,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001217740999891248
+                                                                    "self": 0.0011730989997431607
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05090197800018359,
+                                                            "total": 0.08275230200001715,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005188889999772073,
+                                                            "self": 0.00253729899964128,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00045151199992687907,
+                                                                    "total": 0.00039391300015267916,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00045151199992687907
+                                                                    "self": 0.00039391300015267916
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04829580600016925,
+                                                                    "total": 0.07826742000020204,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04829580600016925
+                                                                    "self": 0.07826742000020204
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016357710001102532,
+                                                                    "total": 0.0015536700000211567,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003321450012663263,
+                                                                    "self": 0.00034412000013617217,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001303625998843927,
+                                                                            "total": 0.0012095499998849846,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001303625998843927
+                                                                            "self": 0.0012095499998849846
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +315,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1278.271958218922,
-                                                    "count": 63546,
+                                                    "total": 1471.9211988529223,
+                                                    "count": 65356,
                                                     "is_parallel": true,
-                                                    "self": 33.307381201932,
+                                                    "self": 33.12207003098706,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.52205219800362,
-                                                            "count": 63546,
+                                                            "total": 22.54704261998154,
+                                                            "count": 65356,
                                                             "is_parallel": true,
-                                                            "self": 22.52205219800362
+                                                            "self": 22.54704261998154
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1118.2564368240892,
-                                                            "count": 63546,
+                                                            "total": 1311.9614781070145,
+                                                            "count": 65356,
                                                             "is_parallel": true,
-                                                            "self": 1118.2564368240892
+                                                            "self": 1311.9614781070145
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 104.1860879948972,
-                                                            "count": 63546,
+                                                            "total": 104.29060809493922,
+                                                            "count": 65356,
                                                             "is_parallel": true,
-                                                            "self": 22.089628185043694,
+                                                            "self": 22.1295470098878,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 82.09645980985351,
-                                                                    "count": 508368,
+                                                                    "total": 82.16106108505141,
+                                                                    "count": 522848,
                                                                     "is_parallel": true,
-                                                                    "self": 82.09645980985351
+                                                                    "self": 82.16106108505141
                                                                 }
                                                             }
                                                         }
@@ -343,31 +355,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 793.1755203239372,
-                            "count": 63547,
-                            "self": 2.8212866139538164,
+                            "total": 749.8827172749636,
+                            "count": 65357,
+                            "self": 2.731102277001355,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 120.13340095297826,
-                                    "count": 63547,
-                                    "self": 119.9970425199781,
+                                    "total": 121.75977067996405,
+                                    "count": 65357,
+                                    "self": 121.5736909379641,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.1363584330001686,
+                                            "total": 0.18607974199994715,
                                             "count": 2,
-                                            "self": 0.1363584330001686
+                                            "self": 0.18607974199994715
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 670.2208327570052,
-                                    "count": 453,
-                                    "self": 274.45810695203363,
+                                    "total": 625.3918443179982,
+                                    "count": 473,
+                                    "self": 405.6678370609952,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 395.7627258049715,
-                                            "count": 22758,
-                                            "self": 395.7627258049715
+                                            "total": 219.724007257003,
+                                            "count": 22752,
+                                            "self": 219.724007257003
                                         }
                                     }
                                 }
@@ -376,19 +388,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.759998308960348e-07,
+                    "total": 8.879997039912269e-07,
                     "count": 1,
-                    "self": 8.759998308960348e-07
+                    "self": 8.879997039912269e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.052604638999582676,
+                    "total": 0.0879109080001399,
                     "count": 1,
-                    "self": 0.0010948049994112807,
+                    "self": 0.0014348859999699926,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.051509834000171395,
+                            "total": 0.0864760220001699,
                             "count": 1,
-                            "self": 0.051509834000171395
+                            "self": 0.0864760220001699
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499966,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499966.onnx",
-                "reward": 0.2457999661564827,
-                "creation_time": 1763068217.4452748,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499966.pt"
-                ]
-            },
             {
                 "steps": 999909,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-999909.onnx",
@@ -27,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000037.pt"
                 ]
+            },
+            {
+                "steps": 1499878,
+                "file_path": "results/Pyramids-Training/Pyramids/Pyramids-1499878.onnx",
+                "reward": 1.7709999904036522,
+                "creation_time": 1763078678.6438942,
+                "auxillary_file_paths": [
+                    "results/Pyramids-Training/Pyramids/Pyramids-1499878.pt"
+                ]
+            },
+            {
+                "steps": 1999911,
+                "file_path": "results/Pyramids-Training/Pyramids/Pyramids-1999911.onnx",
+                "reward": 1.6759999692440033,
+                "creation_time": 1763079926.6173575,
+                "auxillary_file_paths": [
+                    "results/Pyramids-Training/Pyramids/Pyramids-1999911.pt"
+                ]
+            },
+            {
+                "steps": 2000039,
+                "file_path": "results/Pyramids-Training/Pyramids/Pyramids-2000039.onnx",
+                "reward": 1.6759999692440033,
+                "creation_time": 1763079926.715303,
+                "auxillary_file_paths": [
+                    "results/Pyramids-Training/Pyramids/Pyramids-2000039.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000037,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.5193332483371098,
-            "creation_time": 1763069409.8650527,
+            "steps": 2000039,
+            "file_path": "results/Pyramids-Training/Pyramids.onnx",
+            "reward": 1.6759999692440033,
+            "creation_time": 1763079926.715303,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000037.pt"
+                "results/Pyramids-Training/Pyramids/Pyramids-2000039.pt"
             ]
         }
     },