Longer time horizon

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051084b3d0d6aa5299a1990daf4c1564d7525ab21c4635e4b5f49452cb3e4705
+oid sha256:16b843152df875d87d419094587286db6d868bbbb0aa690923d0a736fefdb007
 size 1417437

Pyramids/{Pyramids-1499872.onnx → Pyramids-1499905.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051084b3d0d6aa5299a1990daf4c1564d7525ab21c4635e4b5f49452cb3e4705
+oid sha256:16b843152df875d87d419094587286db6d868bbbb0aa690923d0a736fefdb007
 size 1417437

Pyramids/{Pyramids-499872.pt → Pyramids-1499905.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10494b6fbd3f0a7cae93be2f22866e5192d9977ae15043f81ffe58bfbf355425
+oid sha256:07d52a11439b8e78b97fccf89895f14cc8f498be5658fc30a65a775d9d69081b
 size 8652382

Pyramids/{Pyramids-499872.onnx → Pyramids-1500093.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0710729c75666900978f4e4cfe242c5c3afee5492d565a67752d4770533172e1
+oid sha256:16b843152df875d87d419094587286db6d868bbbb0aa690923d0a736fefdb007
 size 1417437

Pyramids/{Pyramids-1499872.pt → Pyramids-1500093.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92de837ef5221019b19100a4cc393d5ca1f26bb01739f8448909b8b1eb9f7248
+oid sha256:38bc5d07dc337aa128e99faf7b632a4d0219e8a24e41c9d0cc84235f76138997
 size 8652382

Pyramids/{Pyramids-1500128.onnx → Pyramids-499781.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051084b3d0d6aa5299a1990daf4c1564d7525ab21c4635e4b5f49452cb3e4705
+oid sha256:6e13008f3e57dfe9567539f12c63cc189292f3aa2c33f8679b214ebb36b0f17a
 size 1417437

Pyramids/{Pyramids-999919.pt → Pyramids-499781.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1310ead6614f310579ac57fc97abd1fc83c0989329453caf95ba77c15441145f
+oid sha256:6499544cb11149f314ad4e8ed9d81a12983b5149b4ee26af4b52fa43434b1825
 size 8652382

Pyramids/{Pyramids-999919.onnx → Pyramids-999987.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b411018131048425f821a787301ffeebd5917f08efc9da3980aa807b2b771616
+oid sha256:9e953f65c995479db8a562e048fb8d67be68e89b28c3a2f4139c6833c01f1f3e
 size 1417437

Pyramids/{Pyramids-1500128.pt → Pyramids-999987.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46310bf16634f2e48ae402579087866b9dc7d6cac168fcb50d43a5d1ed15defc
+oid sha256:81fad571a40c0c7cf09fc7b25ae86f7b2f8ffb67e60a7203aec5d64ad30dbb71
 size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46310bf16634f2e48ae402579087866b9dc7d6cac168fcb50d43a5d1ed15defc
+oid sha256:38bc5d07dc337aa128e99faf7b632a4d0219e8a24e41c9d0cc84235f76138997
 size 8652382

Pyramids/{events.out.tfevents.1673505416.dc8d7d6d8aff.1226.0 → events.out.tfevents.1673509937.dc8d7d6d8aff.21095.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5db18ac32be3941a8a6f29db971237689a26abd5cbdc2d57f59a141944760ec
-size 489956
+oid sha256:5f95270ce0d18b2d88a944bdc015673586883d3efc5a16775b80a129d40f30e2
+size 471763

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 1500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 1500000, "time_horizon": 256, "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": "Pyramids2", "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

@@ -50,7 +50,7 @@ behaviors:
     keep_checkpoints: 5
     checkpoint_interval: 500000
     max_steps: 1500000
-    time_horizon: 128
+    time_horizon: 256
     summary_freq: 30000
     threaded: false
     self_play: null
@@ -75,7 +75,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55349 [Flags] 2 [Guid] 1205242736 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55284 [Flags] 2 [Guid] 2944578044 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2495:(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  0.081 seconds
+- Completed reload, in  0.077 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: 0.787792 ms
+UnloadTime: 0.867701 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 4 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]: 5149 frames, [32.0 KB-64.0 KB]: 17874 frames, [64.0 KB-128.0 KB]: 5122 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2100 frames, [32.0 KB-64.0 KB]: 19477 frames, [64.0 KB-128.0 KB]: 6580 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
@@ -131,17 +128,17 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       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 7]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -201,22 +198,22 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 6]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 5]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 6]
+    [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -237,28 +234,28 @@ 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]: 27847 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 27859 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 12850
+  Peak main deferred allocation count 12984
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 28145 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 28157 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.7 MB
+      Peak Allocated memory 29.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 28146 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 28158 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.7 MB
+      Peak Allocated memory 26.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -285,15 +282,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 28145 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 28157 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]: 28146 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 28158 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -303,15 +300,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 27847 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 27859 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]: 28145 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 28157 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
@@ -321,21 +318,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 28146 frames
+      Peak usage frame count: [0-1.0 KB]: 28158 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]: 28146 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 28158 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]: 28146 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 28158 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 31.4 KB
@@ -344,4 +341,4 @@ 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":1673507913451,"processId":1270,"allocatedMemory":1963308,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34628},{"Manager":13963},{"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":3808},{"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":1673512371072,"processId":21133,"allocatedMemory":1963308,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34628},{"Manager":13963},{"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":3808},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.27329474687576294,
-            "min": 0.26471900939941406,
-            "max": 1.4313349723815918,
+            "value": 0.327528178691864,
+            "min": 0.327528178691864,
+            "max": 1.4502936601638794,
             "count": 50
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 8273.1787109375,
-            "min": 7979.689453125,
-            "max": 43420.9765625,
+            "value": 9951.6162109375,
+            "min": 9951.6162109375,
+            "max": 46409.3984375,
             "count": 50
         },
         "Pyramids.Step.mean": {
-            "value": 1499872.0,
-            "min": 29986.0,
-            "max": 1499872.0,
+            "value": 1499905.0,
+            "min": 29912.0,
+            "max": 1499905.0,
             "count": 50
         },
         "Pyramids.Step.sum": {
-            "value": 1499872.0,
-            "min": 29986.0,
-            "max": 1499872.0,
+            "value": 1499905.0,
+            "min": 29912.0,
+            "max": 1499905.0,
             "count": 50
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5932605266571045,
-            "min": -0.09740579128265381,
-            "max": 0.6271133422851562,
+            "value": 0.7862254977226257,
+            "min": -0.0986347645521164,
+            "max": 0.7862254977226257,
             "count": 50
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 164.33316040039062,
-            "min": -23.474796295166016,
-            "max": 172.45616149902344,
+            "value": 140.73435974121094,
+            "min": -11.934806823730469,
+            "max": 140.73435974121094,
             "count": 50
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.009621343575417995,
-            "min": -0.007395743392407894,
-            "max": 0.6726012229919434,
+            "value": -0.021666787564754486,
+            "min": -0.028470776975154877,
+            "max": 0.2771379351615906,
             "count": 50
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 2.665112257003784,
-            "min": -2.056016683578491,
-            "max": 160.07908630371094,
+            "value": -3.878355026245117,
+            "min": -4.783090591430664,
+            "max": 33.256553649902344,
             "count": 50
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06729312807631989,
-            "min": 0.06523507990087161,
-            "max": 0.07444782103186849,
+            "value": 0.06795475266324207,
+            "min": 0.06488773596184995,
+            "max": 0.0760969590461734,
             "count": 50
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9421037930684785,
-            "min": 0.5025158296964778,
-            "max": 1.0429928745873562,
+            "value": 0.9513665372853889,
+            "min": 0.4749415263652549,
+            "max": 1.0305533156822684,
             "count": 50
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01582510286728696,
-            "min": 0.0004696144886360367,
-            "max": 0.01582510286728696,
+            "value": 0.01551100939516492,
+            "min": 0.0009322263464162465,
+            "max": 0.016503496621601946,
             "count": 50
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.22155144014201747,
-            "min": 0.005635373863632441,
-            "max": 0.22155144014201747,
+            "value": 0.2171541315323089,
+            "min": 0.010366753799227942,
+            "max": 0.22684459496111442,
             "count": 50
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 3.0406989864666646e-06,
-            "min": 3.0406989864666646e-06,
+            "value": 3.172570371080951e-06,
+            "min": 3.172570371080951e-06,
             "max": 0.00029676708679192377,
             "count": 50
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 4.256978581053331e-05,
-            "min": 4.256978581053331e-05,
-            "max": 0.003470062943312399,
+            "value": 4.441598519513331e-05,
+            "min": 4.441598519513331e-05,
+            "max": 0.0033170318943227996,
             "count": 50
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10101353333333334,
-            "min": 0.10101353333333334,
+            "value": 0.10105749047619049,
+            "min": 0.10105749047619049,
             "max": 0.19892236190476195,
             "count": 50
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4141894666666668,
-            "min": 1.3924565333333336,
-            "max": 2.5066120000000005,
+            "value": 1.4148048666666668,
+            "min": 1.3368084666666666,
+            "max": 2.5056772,
             "count": 50
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00011125197999999994,
-            "min": 0.00011125197999999994,
+            "value": 0.00011564329857142854,
+            "min": 0.00011564329857142854,
             "max": 0.009892343954285714,
             "count": 50
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0015575277199999992,
-            "min": 0.0015575277199999992,
-            "max": 0.11568309123999998,
+            "value": 0.0016190061799999996,
+            "min": 0.0016190061799999996,
+            "max": 0.11059715228,
             "count": 50
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.007782056462019682,
-            "min": 0.007782056462019682,
-            "max": 0.569550633430481,
+            "value": 0.007556379772722721,
+            "min": 0.007414631079882383,
+            "max": 0.46072664856910706,
             "count": 50
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.10894878953695297,
-            "min": 0.10894878953695297,
-            "max": 3.986854314804077,
+            "value": 0.10578931868076324,
+            "min": 0.09769266843795776,
+            "max": 3.2250864505767822,
             "count": 50
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 311.0967741935484,
-            "min": 311.0967741935484,
+            "value": 231.448,
+            "min": 231.448,
             "max": 999.0,
             "count": 50
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28932.0,
-            "min": 16785.0,
-            "max": 32603.0,
+            "value": 28931.0,
+            "min": 15850.0,
+            "max": 33465.0,
             "count": 50
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6458838535572893,
-            "min": -0.9999936006722911,
-            "max": 1.6699574234637808,
+            "value": 1.7674719789028168,
+            "min": -1.0000000596046448,
+            "max": 1.7674719789028168,
             "count": 50
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 153.0671983808279,
-            "min": -31.998001664876938,
-            "max": 156.9759978055954,
+            "value": 220.9339973628521,
+            "min": -28.582001954317093,
+            "max": 225.87839779257774,
             "count": 50
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6458838535572893,
-            "min": -0.9999936006722911,
-            "max": 1.6699574234637808,
+            "value": 1.7674719789028168,
+            "min": -1.0000000596046448,
+            "max": 1.7674719789028168,
             "count": 50
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 153.0671983808279,
-            "min": -31.998001664876938,
-            "max": 156.9759978055954,
+            "value": 220.9339973628521,
+            "min": -28.582001954317093,
+            "max": 225.87839779257774,
             "count": 50
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.025227638135503938,
-            "min": 0.025227638135503938,
-            "max": 11.234559123130406,
+            "value": 0.018012536310357975,
+            "min": 0.018012536310357975,
+            "max": 7.0311954423137335,
             "count": 50
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.346170346601866,
-            "min": 2.346170346601866,
-            "max": 190.9875050932169,
+            "value": 2.2515670387947466,
+            "min": 2.2515670387947466,
+            "max": 161.71749517321587,
             "count": 50
         },
         "Pyramids.IsTraining.mean": {
@@ -184,74 +184,74 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673505413",
+        "start_time_seconds": "1673509934",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids2 --no-graphics",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673507913"
+        "end_time_seconds": "1673512371"
     },
-    "total": 2499.7803211120004,
+    "total": 2436.2943086840005,
     "count": 1,
-    "self": 0.32554824300086693,
+    "self": 0.3218447830004152,
     "children": {
         "run_training.setup": {
-            "total": 0.11094031999999743,
+            "total": 0.1023755930000334,
             "count": 1,
-            "self": 0.11094031999999743
+            "self": 0.1023755930000334
         },
         "TrainerController.start_learning": {
-            "total": 2499.3438325489997,
+            "total": 2435.870088308,
             "count": 1,
-            "self": 1.81582824101406,
+            "self": 1.630570045843342,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.18725368500003,
+                    "total": 6.004141104000155,
                     "count": 1,
-                    "self": 6.18725368500003
+                    "self": 6.004141104000155
                 },
                 "TrainerController.advance": {
-                    "total": 2491.254439477986,
-                    "count": 96030,
-                    "self": 1.7916194849385647,
+                    "total": 2428.1481303021565,
+                    "count": 96814,
+                    "self": 1.7727840980787732,
                     "children": {
                         "env_step": {
-                            "total": 1501.0734431730225,
-                            "count": 96030,
-                            "self": 1344.805394725971,
+                            "total": 1485.060660868984,
+                            "count": 96814,
+                            "self": 1336.6898835476986,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 155.14176123801508,
-                                    "count": 96030,
-                                    "self": 6.315202803994907,
+                                    "total": 147.30312773816877,
+                                    "count": 96814,
+                                    "self": 6.095399021332014,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 148.82655843402017,
-                                            "count": 93818,
-                                            "self": 50.662455443005,
+                                            "total": 141.20772871683675,
+                                            "count": 93858,
+                                            "self": 47.62053048175494,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 98.16410299101517,
-                                                    "count": 93818,
-                                                    "self": 98.16410299101517
+                                                    "total": 93.58719823508181,
+                                                    "count": 93858,
+                                                    "self": 93.58719823508181
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.1262872090363771,
-                                    "count": 96030,
+                                    "total": 1.0676495831166903,
+                                    "count": 96814,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2495.7424857560386,
-                                            "count": 96030,
+                                            "total": 2432.3293087098527,
+                                            "count": 96814,
                                             "is_parallel": true,
-                                            "self": 1283.9770008430874,
+                                            "self": 1224.0753513419404,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.004725247000010313,
+                                                            "total": 0.001793319999706,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003588304000061271,
+                                                            "self": 0.0006566319998455583,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0011369429999490421,
+                                                                    "total": 0.0011366879998604418,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0011369429999490421
+                                                                    "self": 0.0011366879998604418
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03179271199996947,
+                                                            "total": 0.03690019999976357,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00030654399995455606,
+                                                            "self": 0.0005673259984178003,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00029911400002902155,
+                                                                    "total": 0.0005458120003822842,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00029911400002902155
+                                                                    "self": 0.0005458120003822842
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.030156459000011182,
+                                                                    "total": 0.033989833000305225,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.030156459000011182
+                                                                    "self": 0.033989833000305225
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.00103059499997471,
+                                                                    "total": 0.0017972290006582625,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003010249999988446,
+                                                                    "self": 0.0004644370001187781,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0007295699999758654,
+                                                                            "total": 0.0013327920005394844,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0007295699999758654
+                                                                            "self": 0.0013327920005394844
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1211.7654849129513,
-                                                    "count": 96029,
+                                                    "total": 1208.2539573679123,
+                                                    "count": 96813,
                                                     "is_parallel": true,
-                                                    "self": 25.316811974944585,
+                                                    "self": 24.264287808257905,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 18.97805713800642,
-                                                            "count": 96029,
+                                                            "total": 18.58284851092958,
+                                                            "count": 96813,
                                                             "is_parallel": true,
-                                                            "self": 18.97805713800642
+                                                            "self": 18.58284851092958
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1082.4913627549718,
-                                                            "count": 96029,
+                                                            "total": 1072.1948206297984,
+                                                            "count": 96813,
                                                             "is_parallel": true,
-                                                            "self": 1082.4913627549718
+                                                            "self": 1072.1948206297984
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 84.97925304502837,
-                                                            "count": 96029,
+                                                            "total": 93.21200041892644,
+                                                            "count": 96813,
                                                             "is_parallel": true,
-                                                            "self": 21.17682827084502,
+                                                            "self": 21.30576312638459,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 63.80242477418335,
-                                                                    "count": 768232,
+                                                                    "total": 71.90623729254185,
+                                                                    "count": 774504,
                                                                     "is_parallel": true,
-                                                                    "self": 63.80242477418335
+                                                                    "self": 71.90623729254185
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 988.3893768200253,
-                            "count": 96030,
-                            "self": 3.482243689111783,
+                            "total": 941.3146853350936,
+                            "count": 96814,
+                            "self": 3.4799849491882924,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 222.72228986891776,
-                                    "count": 96030,
-                                    "self": 222.4504664269174,
+                                    "total": 194.82750869390202,
+                                    "count": 96814,
+                                    "self": 194.55047395990186,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.27182344200036823,
+                                            "total": 0.27703473400015355,
                                             "count": 3,
-                                            "self": 0.27182344200036823
+                                            "self": 0.27703473400015355
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 762.1848432619958,
-                                    "count": 681,
-                                    "self": 290.307355574984,
+                                    "total": 743.0071916920033,
+                                    "count": 648,
+                                    "self": 282.6112319938966,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 471.87748768701175,
-                                            "count": 34248,
-                                            "self": 471.87748768701175
+                                            "total": 460.3959596981067,
+                                            "count": 34233,
+                                            "self": 460.3959596981067
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.359996511193458e-07,
+                    "total": 9.509994924883358e-07,
                     "count": 1,
-                    "self": 9.359996511193458e-07
+                    "self": 9.509994924883358e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08631020899974828,
+                    "total": 0.08724590500060003,
                     "count": 1,
-                    "self": 0.0012832649999836576,
+                    "self": 0.0012740770007440005,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08502694399976463,
+                            "total": 0.08597182799985603,
                             "count": 1,
-                            "self": 0.08502694399976463
+                            "self": 0.08597182799985603
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,49 +2,49 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499872,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499872.onnx",
-                "reward": null,
-                "creation_time": 1673506216.653944,
+                "steps": 499781,
+                "file_path": "results/Pyramids2/Pyramids/Pyramids-499781.onnx",
+                "reward": 0.361799955368042,
+                "creation_time": 1673510707.2481713,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499872.pt"
+                    "results/Pyramids2/Pyramids/Pyramids-499781.pt"
                 ]
             },
             {
-                "steps": 999919,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999919.onnx",
+                "steps": 999987,
+                "file_path": "results/Pyramids2/Pyramids/Pyramids-999987.onnx",
                 "reward": null,
-                "creation_time": 1673507050.655762,
+                "creation_time": 1673511534.2447195,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999919.pt"
+                    "results/Pyramids2/Pyramids/Pyramids-999987.pt"
                 ]
             },
             {
-                "steps": 1499872,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499872.onnx",
-                "reward": 1.5639999757210414,
-                "creation_time": 1673507913.0333364,
+                "steps": 1499905,
+                "file_path": "results/Pyramids2/Pyramids/Pyramids-1499905.onnx",
+                "reward": 1.824285694531032,
+                "creation_time": 1673512370.698666,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1499872.pt"
+                    "results/Pyramids2/Pyramids/Pyramids-1499905.pt"
                 ]
             },
             {
-                "steps": 1500128,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1500128.onnx",
-                "reward": 1.5639999757210414,
-                "creation_time": 1673507913.182911,
+                "steps": 1500093,
+                "file_path": "results/Pyramids2/Pyramids/Pyramids-1500093.onnx",
+                "reward": 1.8228749781847,
+                "creation_time": 1673512370.8051713,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1500128.pt"
+                    "results/Pyramids2/Pyramids/Pyramids-1500093.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1500128,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.5639999757210414,
-            "creation_time": 1673507913.182911,
+            "steps": 1500093,
+            "file_path": "results/Pyramids2/Pyramids.onnx",
+            "reward": 1.8228749781847,
+            "creation_time": 1673512370.8051713,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1500128.pt"
+                "results/Pyramids2/Pyramids/Pyramids-1500093.pt"
             ]
         }
     },