Trained with time_horizon=256

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b16812aa21571e0fa7ae8656a40683498016376fbb03244e46d2bd42b25a819
+oid sha256:ab3a5b9fe6e4e27fbce3cd1e68925c165e44b4ab0e94f514ff50acfe95e6bbc9
 size 1420238

Pyramids/Pyramids-1000136.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3a5b9fe6e4e27fbce3cd1e68925c165e44b4ab0e94f514ff50acfe95e6bbc9
+size 1420238

Pyramids/Pyramids-1000136.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02acaaf01d9aaf9560f46fea1732ea6ea1c69f1775b3186f874ec7beeb49413a
+size 8656252

Pyramids/Pyramids-499817.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1858b2dcfa90527ec7173a7a1fe43e61ae6f650ddbc2892044673e5a9a60130
+size 1420238

Pyramids/Pyramids-499817.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240cb28e91fd0161523bc3fab8a521f338422552e20dcea069b26260206ae53d
+size 8656173

Pyramids/Pyramids-999928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3a5b9fe6e4e27fbce3cd1e68925c165e44b4ab0e94f514ff50acfe95e6bbc9
+size 1420238

Pyramids/Pyramids-999928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:110ea24ce5a3a80294f1c89ce0d1d1418cd1e05298e1ca0489d703419abadad5
+size 8656173

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa3caa9a904e14557eaa04f8b6cae4e3be069aef6c0d6356ff28e392c08fbe2
+oid sha256:72a4eed4dd055f7d3279263ddb00207718899dd81179075c81e89798decc579e
 size 8655778

Pyramids/events.out.tfevents.1716434593.94659798b8d5.21603.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac559fd749ecddc2736740894a598ae89ea34c729e84242b174a7f8cfe0fd76
+size 781937

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}}, "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": 256, "summary_freq": 10000, "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 1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -52,8 +52,8 @@ behaviors:
     keep_checkpoints: 5
     even_checkpoints: false
     max_steps: 1000000
-    time_horizon: 128
-    summary_freq: 30000
+    time_horizon: 256
+    summary_freq: 10000
     threaded: false
     self_play: null
     behavioral_cloning: null
@@ -79,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids Training 1
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/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] 55443 [Flags] 2 [Guid] 617061137 [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] 55479 [Flags] 2 [Guid] 3458033735 [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/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  0.096 seconds
+- Completed reload, in  0.091 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: 0.813073 ms
+UnloadTime: 1.131369 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4606 frames, [32.0 KB-64.0 KB]: 10890 frames, [64.0 KB-128.0 KB]: 3273 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3577 frames, [32.0 KB-64.0 KB]: 11714 frames, [64.0 KB-128.0 KB]: 3486 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
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       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 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -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]: 18471 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18479 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 12773
+  Peak main deferred allocation count 11956
     [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]: 18769 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18777 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.8 MB
+      Peak Allocated memory 31.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18770 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18778 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.7 MB
+      Peak Allocated memory 21.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ 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]: 18769 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18777 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]: 18770 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18778 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +272,13 @@ 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]: 18471 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18479 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]: 18769 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18777 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
@@ -293,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18770 frames
+      Peak usage frame count: [0-1.0 KB]: 18778 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]: 18770 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18778 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]: 18770 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18778 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":1716434088789,"processId":9668,"allocatedMemory":1970103,"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":3417},{"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":1716436883241,"processId":21638,"allocatedMemory":1970103,"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":3417},{"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.39787694811820984,
-            "min": 0.3890848755836487,
-            "max": 1.3664835691452026,
-            "count": 33
+            "value": 0.3481403589248657,
+            "min": 0.3219470679759979,
+            "max": 1.5952553749084473,
+            "count": 100
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 11910.8447265625,
-            "min": 11753.4755859375,
-            "max": 41453.64453125,
-            "count": 33
+            "value": 3392.279541015625,
+            "min": 3229.9716796875,
+            "max": 19602.498046875,
+            "count": 100
         },
         "Pyramids.Step.mean": {
-            "value": 989912.0,
-            "min": 29952.0,
-            "max": 989912.0,
-            "count": 33
+            "value": 999928.0,
+            "min": 9984.0,
+            "max": 999928.0,
+            "count": 100
         },
         "Pyramids.Step.sum": {
-            "value": 989912.0,
-            "min": 29952.0,
-            "max": 989912.0,
-            "count": 33
+            "value": 999928.0,
+            "min": 9984.0,
+            "max": 999928.0,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.4594818651676178,
-            "min": -0.08148445934057236,
-            "max": 0.559780478477478,
-            "count": 33
+            "value": 0.6715216040611267,
+            "min": -0.11322605609893799,
+            "max": 0.7164641618728638,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 125.89803314208984,
-            "min": -19.637754440307617,
-            "max": 153.37985229492188,
-            "count": 33
+            "value": 38.9482536315918,
+            "min": -4.5290422439575195,
+            "max": 40.12199401855469,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.015083152800798416,
-            "min": -0.002894334029406309,
-            "max": 0.6256721615791321,
-            "count": 33
+            "value": -0.10299792885780334,
+            "min": -0.10299792885780334,
+            "max": 0.43480196595191956,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 4.132783889770508,
-            "min": -0.7554211616516113,
-            "max": 148.2843017578125,
-            "count": 33
+            "value": -5.973879814147949,
+            "min": -5.973879814147949,
+            "max": 17.392078399658203,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06893545644694003,
-            "min": 0.06476758975133122,
-            "max": 0.07267620365833768,
-            "count": 33
+            "value": 0.06717844910956189,
+            "min": 0.06162684253535653,
+            "max": 0.07925617498403881,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9650963902571604,
-            "min": 0.5087334256083638,
-            "max": 1.050167149088035,
-            "count": 33
+            "value": 0.33589224554780944,
+            "min": 0.12955030049973476,
+            "max": 0.38342814044981244,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01583794968049691,
-            "min": 0.0009806812885455184,
-            "max": 0.017336504313875813,
-            "count": 33
+            "value": 0.01792239473434165,
+            "min": 0.0003642205551083558,
+            "max": 0.01889296545414254,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.22173129552695672,
-            "min": 0.013729538039637258,
-            "max": 0.24271106039426138,
-            "count": 33
+            "value": 0.08961197367170826,
+            "min": 0.0007284411102167117,
+            "max": 0.08961197367170826,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.416740384928567e-06,
-            "min": 7.416740384928567e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 1.3214195595599926e-06,
+            "min": 1.3214195595599926e-06,
+            "max": 0.0002981568006144,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010383436538899994,
-            "min": 0.00010383436538899994,
-            "max": 0.003635037188320999,
-            "count": 33
+            "value": 6.607097797799963e-06,
+            "min": 6.607097797799963e-06,
+            "max": 0.0011325766224745,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10247221428571429,
-            "min": 0.10247221428571429,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10044043999999999,
+            "min": 0.10044043999999999,
+            "max": 0.1993856,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.434611,
-            "min": 1.3886848,
-            "max": 2.6116789999999996,
-            "count": 33
+            "value": 0.5022021999999999,
+            "min": 0.3629047000000001,
+            "max": 0.8775255,
+            "count": 100
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025697420714285705,
-            "min": 0.00025697420714285705,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 5.3999955999999754e-05,
+            "min": 5.3999955999999754e-05,
+            "max": 0.00993862144,
+            "count": 100
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.003597638899999999,
-            "min": 0.003597638899999999,
-            "max": 0.1211867321,
-            "count": 33
+            "value": 0.00026999977999999877,
+            "min": 0.00026999977999999877,
+            "max": 0.037764797450000005,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.010397478938102722,
-            "min": 0.01002305094152689,
-            "max": 0.6699055433273315,
-            "count": 33
+            "value": 0.013221800327301025,
+            "min": 0.013021955266594887,
+            "max": 1.007627248764038,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.1455647051334381,
-            "min": 0.1403227150440216,
-            "max": 4.689338684082031,
-            "count": 33
+            "value": 0.06610900163650513,
+            "min": 0.05300857499241829,
+            "max": 2.015254497528076,
+            "count": 100
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 382.55128205128204,
-            "min": 352.30120481927713,
+            "value": 265.4047619047619,
+            "min": 260.25,
             "max": 999.0,
-            "count": 33
+            "count": 98
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29839.0,
-            "min": 15984.0,
-            "max": 32762.0,
-            "count": 33
+            "value": 11147.0,
+            "min": 1760.0,
+            "max": 15984.0,
+            "count": 98
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.4892153680706635,
-            "min": -1.0000000521540642,
-            "max": 1.5753831131810165,
-            "count": 33
+            "value": 1.6843853432957718,
+            "min": -1.0000000596046448,
+            "max": 1.7418107962286151,
+            "count": 99
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 116.15879870951176,
-            "min": -27.69800168275833,
-            "max": 130.75679839402437,
-            "count": 33
+            "value": 69.05979907512665,
+            "min": -16.000000953674316,
+            "max": 69.05979907512665,
+            "count": 99
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.4892153680706635,
-            "min": -1.0000000521540642,
-            "max": 1.5753831131810165,
-            "count": 33
+            "value": 1.6843853432957718,
+            "min": -1.0000000596046448,
+            "max": 1.7418107962286151,
+            "count": 99
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 116.15879870951176,
-            "min": -27.69800168275833,
-            "max": 130.75679839402437,
-            "count": 33
+            "value": 69.05979907512665,
+            "min": -16.000000953674316,
+            "max": 69.05979907512665,
+            "count": 99
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.040505726072296966,
-            "min": 0.03819877009704799,
-            "max": 13.33856382407248,
-            "count": 33
+            "value": 0.03648825318597984,
+            "min": 0.03648825318597984,
+            "max": 9.871843811124563,
+            "count": 99
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.1594466336391633,
-            "min": 3.130790370014438,
-            "max": 213.41702118515968,
-            "count": 33
-        },
-        "Pyramids.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 33
-        },
-        "Pyramids.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 33
+            "value": 1.4960183806251734,
+            "min": 1.1329713931772858,
+            "max": 157.949500977993,
+            "count": 99
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1716431754",
+        "start_time_seconds": "1716434592",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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 ./ml-agents/config/ppo/MyPyramid.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 1 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1716434088"
+        "end_time_seconds": "1716436883"
     },
-    "total": 2333.9169949230004,
+    "total": 2290.3266880849997,
     "count": 1,
-    "self": 0.5263597650009615,
+    "self": 0.4771557589992881,
     "children": {
         "run_training.setup": {
-            "total": 0.05069164299993645,
+            "total": 0.07051015100023506,
             "count": 1,
-            "self": 0.05069164299993645
+            "self": 0.07051015100023506
         },
         "TrainerController.start_learning": {
-            "total": 2333.3399435149995,
+            "total": 2289.779022175,
             "count": 1,
-            "self": 1.6583562220471322,
+            "self": 1.4342343309599528,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.247804358999929,
+                    "total": 2.26019578299929,
                     "count": 1,
-                    "self": 2.247804358999929
+                    "self": 2.26019578299929
                 },
                 "TrainerController.advance": {
-                    "total": 2329.3474767689527,
-                    "count": 63833,
-                    "self": 1.693489429899273,
+                    "total": 2286.0000442570417,
+                    "count": 64081,
+                    "self": 1.4486732639625188,
                     "children": {
                         "env_step": {
-                            "total": 1656.4417198620222,
-                            "count": 63833,
-                            "self": 1506.239680432991,
+                            "total": 1648.9823435820135,
+                            "count": 64081,
+                            "self": 1508.3017766729217,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 149.23766036401048,
-                                    "count": 63833,
-                                    "self": 5.354003195035148,
+                                    "total": 139.79050587699203,
+                                    "count": 64081,
+                                    "self": 4.960329730100966,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 143.88365716897533,
-                                            "count": 62564,
-                                            "self": 143.88365716897533
+                                            "total": 134.83017614689106,
+                                            "count": 62593,
+                                            "self": 134.83017614689106
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9643790650206938,
-                                    "count": 63833,
+                                    "total": 0.8900610320997657,
+                                    "count": 64081,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2327.7188246479595,
-                                            "count": 63833,
+                                            "total": 2284.071174495808,
+                                            "count": 64081,
                                             "is_parallel": true,
-                                            "self": 961.5896535480665,
+                                            "self": 906.0645742377956,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0021729510003751784,
+                                                            "total": 0.0020555150003929157,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006680960000267078,
+                                                            "self": 0.000609143999099615,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015048550003484706,
+                                                                    "total": 0.0014463710012933007,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015048550003484706
+                                                                    "self": 0.0014463710012933007
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05273963099989487,
+                                                            "total": 0.0529998540005181,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006859869995423651,
+                                                            "self": 0.0006919500010553747,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005128230000082112,
+                                                                    "total": 0.00048651699944457505,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005128230000082112
+                                                                    "self": 0.00048651699944457505
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04975501500030077,
+                                                                    "total": 0.049611530999754905,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04975501500030077
+                                                                    "self": 0.049611530999754905
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017858060000435216,
+                                                                    "total": 0.002209856000263244,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004004000006716524,
+                                                                    "self": 0.00042540900085441535,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013854059993718693,
+                                                                            "total": 0.0017844469994088286,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013854059993718693
+                                                                            "self": 0.0017844469994088286
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1366.129171099893,
-                                                    "count": 63832,
+                                                    "total": 1378.0066002580124,
+                                                    "count": 64080,
                                                     "is_parallel": true,
-                                                    "self": 36.41927902207635,
+                                                    "self": 35.05879043918594,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 25.95345729390283,
-                                                            "count": 63832,
+                                                            "total": 25.00306529098907,
+                                                            "count": 64080,
                                                             "is_parallel": true,
-                                                            "self": 25.95345729390283
+                                                            "self": 25.00306529098907
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1195.194154099845,
-                                                            "count": 63832,
+                                                            "total": 1213.3965179539446,
+                                                            "count": 64080,
                                                             "is_parallel": true,
-                                                            "self": 1195.194154099845
+                                                            "self": 1213.3965179539446
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 108.56228068406881,
-                                                            "count": 63832,
+                                                            "total": 104.54822657389286,
+                                                            "count": 64080,
                                                             "is_parallel": true,
-                                                            "self": 22.751277786751416,
+                                                            "self": 21.68169286695047,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 85.8110028973174,
-                                                                    "count": 510656,
+                                                                    "total": 82.86653370694239,
+                                                                    "count": 512640,
                                                                     "is_parallel": true,
-                                                                    "self": 85.8110028973174
+                                                                    "self": 82.86653370694239
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 671.2122674770312,
-                            "count": 63833,
-                            "self": 3.0503544491198227,
+                            "total": 635.5690274110657,
+                            "count": 64081,
+                            "self": 2.789846189916716,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 142.94039209890525,
-                                    "count": 63833,
-                                    "self": 142.67786682590486,
+                                    "total": 117.68227903414572,
+                                    "count": 64081,
+                                    "self": 117.48042283214545,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2625252730003922,
+                                            "total": 0.20185620200027188,
                                             "count": 2,
-                                            "self": 0.2625252730003922
+                                            "self": 0.20185620200027188
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 525.2215209290061,
-                                    "count": 457,
-                                    "self": 311.92183822900097,
+                                    "total": 515.0969021870033,
+                                    "count": 416,
+                                    "self": 304.39398667298883,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 213.29968270000518,
-                                            "count": 22797,
-                                            "self": 213.29968270000518
+                                            "total": 210.70291551401442,
+                                            "count": 22887,
+                                            "self": 210.70291551401442
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.750001481734216e-07,
+                    "total": 8.689994501764886e-07,
                     "count": 1,
-                    "self": 9.750001481734216e-07
+                    "self": 8.689994501764886e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08630518999962078,
+                    "total": 0.08454693499970745,
                     "count": 1,
-                    "self": 0.0013683369998034323,
+                    "self": 0.0013945529990451178,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08493685299981735,
+                            "total": 0.08315238200066233,
                             "count": 1,
-                            "self": 0.08493685299981735
+                            "self": 0.08315238200066233
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499990,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499990.onnx",
-                "reward": null,
-                "creation_time": 1716432850.5277398,
+                "steps": 499817,
+                "file_path": "results/Pyramids Training 1/Pyramids/Pyramids-499817.onnx",
+                "reward": 1.391499936580658,
+                "creation_time": 1716435623.5685778,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499990.pt"
+                    "results/Pyramids Training 1/Pyramids/Pyramids-499817.pt"
                 ]
             },
             {
-                "steps": 999976,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999976.onnx",
-                "reward": 1.7535000070929527,
-                "creation_time": 1716434088.2100024,
+                "steps": 999928,
+                "file_path": "results/Pyramids Training 1/Pyramids/Pyramids-999928.onnx",
+                "reward": 1.676000028848648,
+                "creation_time": 1716436882.7105162,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999976.pt"
+                    "results/Pyramids Training 1/Pyramids/Pyramids-999928.pt"
                 ]
             },
             {
-                "steps": 1000104,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000104.onnx",
-                "reward": 1.7535000070929527,
-                "creation_time": 1716434088.308204,
+                "steps": 1000136,
+                "file_path": "results/Pyramids Training 1/Pyramids/Pyramids-1000136.onnx",
+                "reward": 1.7345000058412552,
+                "creation_time": 1716436882.8116915,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000104.pt"
+                    "results/Pyramids Training 1/Pyramids/Pyramids-1000136.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000104,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7535000070929527,
-            "creation_time": 1716434088.308204,
+            "steps": 1000136,
+            "file_path": "results/Pyramids Training 1/Pyramids.onnx",
+            "reward": 1.7345000058412552,
+            "creation_time": 1716436882.8116915,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000104.pt"
+                "results/Pyramids Training 1/Pyramids/Pyramids-1000136.pt"
             ]
         }
     },