FirstTry

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bc4a883acff3e80e04592e2dab832b29e0b373966d901127d057e9bfe4a1df
-size 2469240
+oid sha256:9e32b8dfe4121d2bdfcabbe25bc9c3687d842952b6ef5de6bce7eb5726398063
+size 1418184

Pyramids/Pyramids-1499934.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a99dd65fdab36bbb7857cf2a0c24c60fab315cd3a32214c16bafbd2e885fb8b
+size 1418184

Pyramids/Pyramids-1499934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:215cde9422a59c17abcb16c19fbd0acb25a86ed7c63c3405edab7df37962045a
+size 8650990

Pyramids/Pyramids-1999989.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe1c0ce2258c7c3d2a3d74860c1540761b19e08fe7c8b4494305b357885e691
+size 1418184

Pyramids/Pyramids-1999989.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e816f9e549e1ee65b7a1816825b35e120b392ef610ac7e32480c4bd57ce5d9
+size 8650990

Pyramids/Pyramids-2245193.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e32b8dfe4121d2bdfcabbe25bc9c3687d842952b6ef5de6bce7eb5726398063
+size 1418184

Pyramids/Pyramids-2245193.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0445dcdaa7d14554b06d72f4a39c940e738837db42972177f65116b50a524f
+size 8650990

Pyramids/Pyramids-237048.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84dc4d4607be1f8da9f65a1fe7820d7ff4366fbdfb9cd9f1943925c0a7dfeee
+size 2469240

Pyramids/Pyramids-237048.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a45846c21e156e36bfd5892586bb5fae9c2c34bc12054b8ce155129ddbe193
+size 16305482

Pyramids/Pyramids-499985.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877b0d985ecf07f55677d0937f3d4f64d18670c1420b31a9861f2ce27fa3447a
+size 1418184

Pyramids/Pyramids-499985.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa66494ad7af5778830f90bb8c4ae69ba07f243ed8dff476c951ad487042c87
+size 8650990

Pyramids/Pyramids-999898.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb7e1a47801464fc116f9be9f807cfd1b5e46eb59cc5e548d617a541f019f5a
+size 1418184

Pyramids/Pyramids-999898.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3039458c22bba05b264782ee8f7c35e149bd7626209fd4b0179f7e4fea73ed2
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc1a4f2e043ff8039fb14124877a62ab3745dead41bd52d50b803de2170a660
-size 16305482
+oid sha256:cb0445dcdaa7d14554b06d72f4a39c940e738837db42972177f65116b50a524f
+size 8650990

Pyramids/{events.out.tfevents.1679310820.2be6cd0fd31e.7766.0 → events.out.tfevents.1679311368.2be6cd0fd31e.10363.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ced11ef5c47a5a537e829ab45ca4dd433a301b08028db830138a3201ca6789
-size 32622
+oid sha256:d348ee1ba8efbe7b710d6ed66a4203d7a5de7cf37296979d4a6de5439347488b
+size 682757

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": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "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": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.015, "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": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -18,7 +18,7 @@ behaviors:
     network_settings:
       normalize: false
       hidden_units: 512
-      num_layers: 3
+      num_layers: 2
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -35,23 +35,23 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-      curiosity:
+      rnd:
         gamma: 0.99
-        strength: 0.02
+        strength: 0.015
         network_settings:
           normalize: false
-          hidden_units: 256
-          num_layers: 2
+          hidden_units: 64
+          num_layers: 3
           vis_encode_type: simple
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-        learning_rate: 0.0003
+        learning_rate: 0.0001
         encoding_size: null
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 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] 55038 [Flags] 2 [Guid] 3150912432 [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] 55022 [Flags] 2 [Guid] 4169250087 [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'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +33,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.082 seconds
+- Completed reload, in  0.126 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,7 +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: 0.835221 ms
+UnloadTime: 0.959393 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 1149 frames, [32.0 KB-64.0 KB]: 779 frames, [64.0 KB-128.0 KB]: 94 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 6119 frames, [32.0 KB-64.0 KB]: 25602 frames, [64.0 KB-128.0 KB]: 10396 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
@@ -146,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -183,12 +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
@@ -204,28 +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]: 1724 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 41819 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 12451
+  Peak main deferred allocation count 12584
     [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]: 2022 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 42117 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.6 MB
+      Peak Allocated memory 29.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 2023 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 42118 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.8 MB
+      Peak Allocated memory 24.1 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,13 +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]: 2022 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 42117 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]: 2023 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 42118 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,16 +272,16 @@ 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]: 1724 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 41819 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]: 2022 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 42117 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
-      Peak Allocated memory 4.7 MB
+      Peak Block count 1
+      Peak Allocated memory 3.9 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -290,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 2023 frames
+      Peak usage frame count: [0-1.0 KB]: 42118 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]: 2023 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 42118 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]: 2023 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 42118 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 29.1 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679311042069,"processId":7786,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679316493431,"processId":10387,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,261 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.7332426905632019,
-            "min": 0.7332426905632019,
-            "max": 1.47197687625885,
-            "count": 3
+            "value": 0.21305184066295624,
+            "min": 0.21279378235340118,
+            "max": 1.406337857246399,
+            "count": 74
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 21821.302734375,
-            "min": 21821.302734375,
-            "max": 44653.890625,
-            "count": 3
+            "value": 6394.9638671875,
+            "min": 6342.95703125,
+            "max": 42662.6640625,
+            "count": 74
         },
         "Pyramids.Step.mean": {
-            "value": 89892.0,
-            "min": 29999.0,
-            "max": 89892.0,
-            "count": 3
+            "value": 2219894.0,
+            "min": 29952.0,
+            "max": 2219894.0,
+            "count": 74
         },
         "Pyramids.Step.sum": {
-            "value": 89892.0,
-            "min": 29999.0,
-            "max": 89892.0,
-            "count": 3
+            "value": 2219894.0,
+            "min": 29952.0,
+            "max": 2219894.0,
+            "count": 74
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.09850305318832397,
-            "min": -0.09850305318832397,
-            "max": -0.010852432809770107,
-            "count": 3
+            "value": 0.7108884453773499,
+            "min": -0.10718224197626114,
+            "max": 0.7917513251304626,
+            "count": 74
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -23.739234924316406,
-            "min": -23.739234924316406,
-            "max": -2.582879066467285,
-            "count": 3
-        },
-        "Pyramids.Policy.CuriosityValueEstimate.mean": {
-            "value": 0.29356181621551514,
-            "min": 0.1554223895072937,
-            "max": 0.4291464686393738,
-            "count": 3
-        },
-        "Pyramids.Policy.CuriosityValueEstimate.sum": {
-            "value": 70.74839782714844,
-            "min": 36.99052810668945,
-            "max": 103.85344696044922,
-            "count": 3
+            "value": 204.73587036132812,
+            "min": -25.830921173095703,
+            "max": 232.68447875976562,
+            "count": 74
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.002068731002509594,
+            "min": -0.022476624697446823,
+            "max": 0.718090832233429,
+            "count": 74
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -0.5957944989204407,
+            "min": -6.315931797027588,
+            "max": 170.18753051757812,
+            "count": 74
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0686513939106717,
-            "min": 0.0686513939106717,
-            "max": 0.07443957133030535,
-            "count": 3
+            "value": 0.06896385410024473,
+            "min": 0.06306390306313656,
+            "max": 0.07312573167369041,
+            "count": 74
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.8238167269280603,
-            "min": 0.5955165706424428,
-            "max": 0.8238167269280603,
-            "count": 3
+            "value": 1.034457811503671,
+            "min": 0.505250734832384,
+            "max": 1.0886483086893957,
+            "count": 74
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.002036700791027665,
-            "min": 0.0019856485650744282,
-            "max": 0.003455981005490931,
-            "count": 3
+            "value": 0.014182371119709892,
+            "min": 0.00018780713212033948,
+            "max": 0.022046837682957454,
+            "count": 74
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.02444040949233198,
-            "min": 0.02184213421581871,
-            "max": 0.027647848043927448,
-            "count": 3
+            "value": 0.2127355667956484,
+            "min": 0.0024414927175644132,
+            "max": 0.2347687060742721,
+            "count": 74
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 0.00027732408255864163,
-            "min": 0.00027732408255864163,
-            "max": 0.0002948491142169625,
-            "count": 3
+            "value": 7.948783350407998e-05,
+            "min": 7.948783350407998e-05,
+            "max": 0.00029838354339596195,
+            "count": 74
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0033278889907037,
-            "min": 0.0023587929137357,
-            "max": 0.0033278889907037,
-            "count": 3
+            "value": 0.0011923175025611997,
+            "min": 0.0011554058148650665,
+            "max": 0.0039690149769950325,
+            "count": 74
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.19244135833333334,
-            "min": 0.19244135833333334,
-            "max": 0.1982830375,
-            "count": 3
+            "value": 0.12649592,
+            "min": 0.12649592,
+            "max": 0.19946118095238097,
+            "count": 74
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 2.3092963,
-            "min": 1.5862643,
-            "max": 2.3092963,
-            "count": 3
+            "value": 1.8974388000000002,
+            "min": 1.3962282666666668,
+            "max": 2.797435233333333,
+            "count": 74
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.009244891697500002,
-            "min": 0.009244891697500002,
-            "max": 0.009828475446249998,
-            "count": 3
+            "value": 0.002656942408,
+            "min": 0.002656942408,
+            "max": 0.009946171977142856,
+            "count": 74
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.11093870037000002,
-            "min": 0.07862780356999999,
-            "max": 0.11093870037000002,
-            "count": 3
-        },
-        "Pyramids.Losses.CuriosityForwardLoss.mean": {
-            "value": 0.11513036146745208,
-            "min": 0.11513036146745208,
-            "max": 0.3928404946637833,
-            "count": 3
-        },
-        "Pyramids.Losses.CuriosityForwardLoss.sum": {
-            "value": 1.3815643376094249,
-            "min": 1.3815643376094249,
-            "max": 3.1427239573102663,
-            "count": 3
-        },
-        "Pyramids.Losses.CuriosityInverseLoss.mean": {
-            "value": 0.30047359277178154,
-            "min": 0.30047359277178154,
-            "max": 0.717943143971129,
-            "count": 3
-        },
-        "Pyramids.Losses.CuriosityInverseLoss.sum": {
-            "value": 3.6056831132613785,
-            "min": 3.6056831132613785,
-            "max": 5.743545151769032,
-            "count": 3
+            "value": 0.03985413612,
+            "min": 0.03861497984,
+            "max": 0.13230819617,
+            "count": 74
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.004872409626841545,
+            "min": 0.004872409626841545,
+            "max": 0.5501860976219177,
+            "count": 74
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.07308614253997803,
+            "min": 0.06851315498352051,
+            "max": 3.8513028621673584,
+            "count": 74
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 963.969696969697,
-            "min": 957.6571428571428,
-            "max": 963.969696969697,
-            "count": 3
+            "value": 267.92857142857144,
+            "min": 239.40869565217392,
+            "max": 999.0,
+            "count": 74
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31811.0,
-            "min": 16286.0,
-            "max": 33518.0,
-            "count": 3
+            "value": 30008.0,
+            "min": 15984.0,
+            "max": 32628.0,
+            "count": 74
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.7829333837285186,
-            "min": -0.8412941676728866,
-            "max": -0.7829333837285186,
-            "count": 3
+            "value": 1.6952178411717926,
+            "min": -1.0000000521540642,
+            "max": 1.756663780145604,
+            "count": 74
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -25.836801663041115,
-            "min": -27.548801690340042,
-            "max": -14.302000850439072,
-            "count": 3
+            "value": 189.86439821124077,
+            "min": -32.000001668930054,
+            "max": 218.70319747924805,
+            "count": 74
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.7829333837285186,
-            "min": -0.8412941676728866,
-            "max": -0.7829333837285186,
-            "count": 3
+            "value": 1.6952178411717926,
+            "min": -1.0000000521540642,
+            "max": 1.756663780145604,
+            "count": 74
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -25.836801663041115,
-            "min": -27.548801690340042,
-            "max": -14.302000850439072,
-            "count": 3
-        },
-        "Pyramids.Policy.CuriosityReward.mean": {
-            "value": 2.408704619967576,
-            "min": 2.408704619967576,
-            "max": 5.9998919543098,
-            "count": 3
-        },
-        "Pyramids.Policy.CuriosityReward.sum": {
-            "value": 79.48725245893002,
-            "min": 79.48725245893002,
-            "max": 167.22194342315197,
-            "count": 3
+            "value": 189.86439821124077,
+            "min": -32.000001668930054,
+            "max": 218.70319747924805,
+            "count": 74
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.020227364534548542,
+            "min": 0.0186800462162927,
+            "max": 17.862700942903757,
+            "count": 74
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.2654648278694367,
+            "min": 2.166885361089953,
+            "max": 285.8032150864601,
+            "count": 74
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 3
+            "count": 74
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 3
+            "count": 74
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679310817",
+        "start_time_seconds": "1679311364",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Pyramids.yaml --force --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --force --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1679311042"
+        "end_time_seconds": "1679316493"
     },
-    "total": 224.99845064800002,
+    "total": 5128.685583266,
     "count": 1,
-    "self": 0.39462591000028624,
+    "self": 0.37654672500138986,
     "children": {
         "run_training.setup": {
-            "total": 0.10343692399987958,
+            "total": 0.19419290999985606,
             "count": 1,
-            "self": 0.10343692399987958
+            "self": 0.19419290999985606
         },
         "TrainerController.start_learning": {
-            "total": 224.50038781399985,
+            "total": 5128.1148436309995,
             "count": 1,
-            "self": 0.13897747199507648,
+            "self": 2.993000362969724,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.768903350000073,
+                    "total": 5.96526085000005,
                     "count": 1,
-                    "self": 5.768903350000073
+                    "self": 5.96526085000005
                 },
                 "TrainerController.advance": {
-                    "total": 218.3538173340046,
-                    "count": 6767,
-                    "self": 0.16342469497431011,
+                    "total": 5119.012813234029,
+                    "count": 145098,
+                    "self": 3.3753958423458243,
                     "children": {
                         "env_step": {
-                            "total": 143.28279221701564,
-                            "count": 6767,
-                            "self": 131.14333348503055,
+                            "total": 3750.0977920628043,
+                            "count": 145098,
+                            "self": 3513.8051432639236,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 12.054268244993636,
-                                    "count": 6767,
-                                    "self": 0.4964715519888614,
+                                    "total": 234.46264572097107,
+                                    "count": 145098,
+                                    "self": 10.283723418860973,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 11.557796693004775,
-                                            "count": 6743,
-                                            "self": 11.557796693004775
+                                            "total": 224.1789223021101,
+                                            "count": 140391,
+                                            "self": 224.1789223021101
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.0851904869914506,
-                                    "count": 6766,
+                                    "total": 1.8300030779096232,
+                                    "count": 145098,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 223.88274269401904,
-                                            "count": 6766,
+                                            "total": 5118.116264883935,
+                                            "count": 145098,
                                             "is_parallel": true,
-                                            "self": 105.22172793302866,
+                                            "self": 1859.8603183498399,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0017692200001420133,
+                                                            "total": 0.002644625999892014,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005908599994199903,
+                                                            "self": 0.0007174199995461095,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001178360000722023,
+                                                                    "total": 0.0019272060003459046,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001178360000722023
+                                                                    "self": 0.0019272060003459046
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.050683017999972435,
+                                                            "total": 0.0464308959999471,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0012719580001885333,
+                                                            "self": 0.0005561479993048124,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00048588999993626203,
+                                                                    "total": 0.0004710110001724388,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00048588999993626203
+                                                                    "self": 0.0004710110001724388
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04660584699990977,
+                                                                    "total": 0.04371357200034254,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04660584699990977
+                                                                    "self": 0.04371357200034254
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0023193229999378673,
+                                                                    "total": 0.0016901650001273083,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005330709998361272,
+                                                                    "self": 0.000376553001387947,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0017862520001017401,
+                                                                            "total": 0.0013136119987393613,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0017862520001017401
+                                                                            "self": 0.0013136119987393613
                                                                         }
                                                                     }
                                                                 }
@@ -315,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 118.66101476099038,
-                                                    "count": 6765,
+                                                    "total": 3258.2559465340955,
+                                                    "count": 145097,
                                                     "is_parallel": true,
-                                                    "self": 3.2112689710043014,
+                                                    "self": 68.57586587011201,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.370272765999971,
-                                                            "count": 6765,
+                                                            "total": 49.47966687392545,
+                                                            "count": 145097,
                                                             "is_parallel": true,
-                                                            "self": 2.370272765999971
+                                                            "self": 49.47966687392545
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 103.60581320198776,
-                                                            "count": 6765,
+                                                            "total": 2939.0468410551134,
+                                                            "count": 145097,
                                                             "is_parallel": true,
-                                                            "self": 103.60581320198776
+                                                            "self": 2939.0468410551134
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 9.473659821998353,
-                                                            "count": 6765,
+                                                            "total": 201.15357273494465,
+                                                            "count": 145097,
                                                             "is_parallel": true,
-                                                            "self": 1.98855490801202,
+                                                            "self": 42.925451134095965,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 7.4851049139863335,
-                                                                    "count": 54120,
+                                                                    "total": 158.22812160084868,
+                                                                    "count": 1160776,
                                                                     "is_parallel": true,
-                                                                    "self": 7.4851049139863335
+                                                                    "self": 158.22812160084868
                                                                 }
                                                             }
                                                         }
@@ -355,24 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 74.90760042201464,
-                            "count": 6766,
-                            "self": 0.19026733500504633,
+                            "total": 1365.539625328879,
+                            "count": 145098,
+                            "self": 5.832565513886038,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 11.483589693009435,
-                                    "count": 6766,
-                                    "self": 11.483589693009435
+                                    "total": 260.18479623999565,
+                                    "count": 145098,
+                                    "self": 259.80453503099534,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.38026120900030946,
+                                            "count": 4,
+                                            "self": 0.38026120900030946
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 63.23374339400016,
-                                    "count": 39,
-                                    "self": 42.85521611799845,
+                                    "total": 1099.5222635749974,
+                                    "count": 1034,
+                                    "self": 699.7570022299469,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 20.378527276001705,
-                                            "count": 2451,
-                                            "self": 20.378527276001705
+                                            "total": 399.7652613450505,
+                                            "count": 51205,
+                                            "self": 399.7652613450505
                                         }
                                     }
                                 }
@@ -381,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2810000953322742e-06,
+                    "total": 3.5860002753906883e-06,
                     "count": 1,
-                    "self": 1.2810000953322742e-06
+                    "self": 3.5860002753906883e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.23868837700001677,
+                    "total": 0.14376559800075484,
                     "count": 1,
-                    "self": 0.005373185000053127,
+                    "self": 0.0038810860005469294,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.23331519199996364,
+                            "total": 0.1398845120002079,
                             "count": 1,
-                            "self": 0.23331519199996364
+                            "self": 0.1398845120002079
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 106651,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-106651.onnx",
+                "steps": 499985,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499985.onnx",
+                "reward": -0.999800056219101,
+                "creation_time": 1679312341.494911,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-499985.pt"
+                ]
+            },
+            {
+                "steps": 999898,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999898.onnx",
+                "reward": 1.7650000005960464,
+                "creation_time": 1679313491.4655182,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999898.pt"
+                ]
+            },
+            {
+                "steps": 1499934,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499934.onnx",
+                "reward": null,
+                "creation_time": 1679314687.4309547,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499934.pt"
+                ]
+            },
+            {
+                "steps": 1999989,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999989.onnx",
+                "reward": 1.784333328406016,
+                "creation_time": 1679315900.2692406,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999989.pt"
+                ]
+            },
+            {
+                "steps": 2245193,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2245193.onnx",
                 "reward": null,
-                "creation_time": 1679311041.7314353,
+                "creation_time": 1679316493.1184192,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-106651.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2245193.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 106651,
+            "steps": 2245193,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
             "reward": null,
-            "creation_time": 1679311041.7314353,
+            "creation_time": 1679316493.1184192,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-106651.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2245193.pt"
             ]
         }
     },