Second Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d152544224f9c352dff1e75725a47ac5d89909cc9bce2a07470b20a7d523dc5
+oid sha256:14d4790674e9622aad839d0ba5e6ac738a0c9b5fd4f7edff0984526cc40748bf
 size 1418184

Pyramids/Pyramids-1365633.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d4790674e9622aad839d0ba5e6ac738a0c9b5fd4f7edff0984526cc40748bf
+size 1418184

Pyramids/Pyramids-1365633.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ea0e9aa0f2fe922164398d3f6ed0b79f0cecce014a9a58b6c19e14afc39b2f
+size 8650990

Pyramids/Pyramids-499907.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371df533a2950a9fae09fabd88682ec606c0933db44ada7a491302050eacf70f
+size 1418184

Pyramids/Pyramids-499907.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6dbd38e67216bf9c5b0ac58db3ddf558495f4407decad370931c94575595ce
+size 8650990

Pyramids/Pyramids-999994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8049d94e08acb663f132f077cecddbe49690b2c00b07651edf8b20413f993dd3
+size 1418184

Pyramids/Pyramids-999994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513a7b2762718eec1197b7026e2ceca3eff36fd1518d794e4001bc9428516828
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1e76308f6f4f129591c85525507b14103369db3849703f8424add2986addc9
+oid sha256:87ea0e9aa0f2fe922164398d3f6ed0b79f0cecce014a9a58b6c19e14afc39b2f
 size 8650990

Pyramids/events.out.tfevents.1691750877.a1aa58169c4f.3559.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aceccfeead16575b31be3fc634e1ba20dd59eb639ac16c2a505e3fabf691e7d
+size 457183

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 1500000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -81,7 +81,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55371 [Flags] 2 [Guid] 2971349638 [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] 55352 [Flags] 2 [Guid] 1547603162 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.150 seconds
+- Completed reload, in  0.098 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: 1.205508 ms
+UnloadTime: 0.888052 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 7151 frames, [32.0 KB-64.0 KB]: 9532 frames, [64.0 KB-128.0 KB]: 2082 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3219 frames, [32.0 KB-64.0 KB]: 18063 frames, [64.0 KB-128.0 KB]: 4339 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 25323 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 12720
+  Peak main deferred allocation count 11181
     [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]: 18765 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 25621 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.2 MB
+      Peak Allocated memory 30.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18766 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 25622 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.1 MB
+      Peak Allocated memory 22.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18765 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 25621 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]: 18766 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 25622 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 25323 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]: 18765 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 25621 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -293,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18766 frames
+      Peak usage frame count: [0-1.0 KB]: 25622 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]: 18766 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 25622 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]: 18766 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 25622 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1691702607887,"processId":27588,"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":1691754662335,"processId":3579,"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.539826512336731,
-            "min": 0.47692787647247314,
-            "max": 1.2591854333877563,
-            "count": 33
+            "value": 0.27999401092529297,
+            "min": 0.2584760785102844,
+            "max": 1.4691399335861206,
+            "count": 45
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 16263.8935546875,
-            "min": 14315.466796875,
-            "max": 38198.6484375,
-            "count": 33
+            "value": 8489.41796875,
+            "min": 7729.46826171875,
+            "max": 44567.828125,
+            "count": 45
         },
         "Pyramids.Step.mean": {
-            "value": 989954.0,
-            "min": 29957.0,
-            "max": 989954.0,
-            "count": 33
+            "value": 1349874.0,
+            "min": 29952.0,
+            "max": 1349874.0,
+            "count": 45
         },
         "Pyramids.Step.sum": {
-            "value": 989954.0,
-            "min": 29957.0,
-            "max": 989954.0,
-            "count": 33
+            "value": 1349874.0,
+            "min": 29952.0,
+            "max": 1349874.0,
+            "count": 45
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.3512098789215088,
-            "min": -0.10250982642173767,
-            "max": 0.3512098789215088,
-            "count": 33
+            "value": 0.5843580961227417,
+            "min": -0.09230305254459381,
+            "max": 0.623251736164093,
+            "count": 45
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 92.71940612792969,
-            "min": -24.70486831665039,
-            "max": 92.71940612792969,
-            "count": 33
+            "value": 161.2828369140625,
+            "min": -22.152732849121094,
+            "max": 177.0034942626953,
+            "count": 45
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.01374595332890749,
-            "min": 0.006082380656152964,
-            "max": 0.6945539116859436,
-            "count": 33
+            "value": 0.03263590857386589,
+            "min": -0.03559710457921028,
+            "max": 0.24793276190757751,
+            "count": 45
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 3.628931760787964,
-            "min": 1.5996661186218262,
-            "max": 165.3038330078125,
-            "count": 33
+            "value": 9.007511138916016,
+            "min": -9.753606796264648,
+            "max": 58.76006317138672,
+            "count": 45
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06756214899038185,
-            "min": 0.06501269108304071,
-            "max": 0.07635329224061618,
-            "count": 33
+            "value": 0.07196356706637223,
+            "min": 0.06517991559196483,
+            "max": 0.07228699586507605,
+            "count": 45
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9458700858653459,
-            "min": 0.6108263379249295,
-            "max": 1.1167734275770593,
-            "count": 33
+            "value": 1.0074899389292113,
+            "min": 0.4962817789593995,
+            "max": 1.04574709889358,
+            "count": 45
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01387963175410801,
-            "min": 7.140849419619032e-05,
-            "max": 0.013946470414382585,
-            "count": 33
+            "value": 0.014598498705752371,
+            "min": 0.000496700446871436,
+            "max": 0.014598498705752371,
+            "count": 45
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.19431484455751213,
-            "min": 0.0010711274129428549,
-            "max": 0.19525058580135618,
-            "count": 33
+            "value": 0.2043789818805332,
+            "min": 0.006457105809328668,
+            "max": 0.20839173290490481,
+            "count": 45
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.514497495200001e-06,
-            "min": 7.514497495200001e-06,
-            "max": 0.0002948538392153875,
-            "count": 33
+            "value": 3.3119403245942855e-05,
+            "min": 3.3119403245942855e-05,
+            "max": 0.00029676708679192377,
+            "count": 45
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010520296493280002,
-            "min": 0.00010520296493280002,
-            "max": 0.0036362008879330995,
-            "count": 33
+            "value": 0.0004636716454432,
+            "min": 0.0004636716454432,
+            "max": 0.003822684125771999,
+            "count": 45
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1025048,
-            "min": 0.1025048,
-            "max": 0.1982846125,
-            "count": 33
+            "value": 0.11103977142857144,
+            "min": 0.11103977142857144,
+            "max": 0.19892236190476195,
+            "count": 45
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4350672,
-            "min": 1.4350672,
-            "max": 2.6120669000000007,
-            "count": 33
+            "value": 1.5545568,
+            "min": 1.3924565333333336,
+            "max": 2.674228,
+            "count": 45
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002602295200000001,
-            "min": 0.0002602295200000001,
-            "max": 0.00982863278875,
-            "count": 33
+            "value": 0.001112873165714286,
+            "min": 0.001112873165714286,
+            "max": 0.009892343954285714,
+            "count": 45
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036432132800000012,
-            "min": 0.0036432132800000012,
-            "max": 0.12122548331,
-            "count": 33
+            "value": 0.015580224320000002,
+            "min": 0.015580224320000002,
+            "max": 0.1274353772,
+            "count": 45
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.016054445877671242,
-            "min": 0.016054445877671242,
-            "max": 0.5237568616867065,
-            "count": 33
+            "value": 0.008267933502793312,
+            "min": 0.00725268479436636,
+            "max": 0.2745141386985779,
+            "count": 45
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.22476224601268768,
-            "min": 0.22476224601268768,
-            "max": 4.190054893493652,
-            "count": 33
+            "value": 0.11575107276439667,
+            "min": 0.10153758525848389,
+            "max": 1.92159903049469,
+            "count": 45
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 530.948275862069,
-            "min": 499.57377049180326,
-            "max": 989.1875,
-            "count": 33
+            "value": 336.34090909090907,
+            "min": 315.21590909090907,
+            "max": 999.0,
+            "count": 45
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30795.0,
-            "min": 16244.0,
-            "max": 34057.0,
-            "count": 33
+            "value": 29598.0,
+            "min": 15984.0,
+            "max": 33308.0,
+            "count": 45
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.2620930783450603,
-            "min": -0.9997448795314493,
-            "max": 1.2669708903540264,
-            "count": 33
+            "value": 1.549988615157252,
+            "min": -1.0000000521540642,
+            "max": 1.6620522551238537,
+            "count": 45
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 73.2013985440135,
-            "min": -28.99260150641203,
-            "max": 73.2013985440135,
-            "count": 33
+            "value": 136.39899813383818,
+            "min": -29.54780162125826,
+            "max": 146.26059845089912,
+            "count": 45
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.2620930783450603,
-            "min": -0.9997448795314493,
-            "max": 1.2669708903540264,
-            "count": 33
+            "value": 1.549988615157252,
+            "min": -1.0000000521540642,
+            "max": 1.6620522551238537,
+            "count": 45
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 73.2013985440135,
-            "min": -28.99260150641203,
-            "max": 73.2013985440135,
-            "count": 33
+            "value": 136.39899813383818,
+            "min": -29.54780162125826,
+            "max": 146.26059845089912,
+            "count": 45
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.08800474903797169,
-            "min": 0.08690998291713185,
-            "max": 10.602918975274353,
-            "count": 33
+            "value": 0.027509241803355424,
+            "min": 0.0264230206602709,
+            "max": 5.217091434635222,
+            "count": 45
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 5.104275444202358,
-            "min": 4.780049060442252,
-            "max": 180.249622579664,
-            "count": 33
+            "value": 2.4208132786952774,
+            "min": 2.246325553089264,
+            "max": 83.47346295416355,
+            "count": 45
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 45
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 45
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1691700360",
+        "start_time_seconds": "1691750876",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
         "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": "1691702607"
+        "end_time_seconds": "1691754662"
     },
-    "total": 2247.1883790089996,
+    "total": 3786.0023300489997,
     "count": 1,
-    "self": 0.49505610700089164,
+    "self": 1.0648708260000603,
     "children": {
         "run_training.setup": {
-            "total": 0.07632604499940498,
+            "total": 0.04659137900000587,
             "count": 1,
-            "self": 0.07632604499940498
+            "self": 0.04659137900000587
         },
         "TrainerController.start_learning": {
-            "total": 2246.6169968569993,
+            "total": 3784.890867844,
             "count": 1,
-            "self": 1.7081023310820456,
+            "self": 2.9133006480246877,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.85127133900005,
+                    "total": 4.779982707000045,
                     "count": 1,
-                    "self": 4.85127133900005
+                    "self": 4.779982707000045
                 },
                 "TrainerController.advance": {
-                    "total": 2239.9597937149165,
-                    "count": 63457,
-                    "self": 1.5843999690550845,
+                    "total": 3776.907284288975,
+                    "count": 87158,
+                    "self": 2.778459381104767,
                     "children": {
                         "env_step": {
-                            "total": 1556.629405039821,
-                            "count": 63457,
-                            "self": 1434.8015486668146,
+                            "total": 2721.368848492936,
+                            "count": 87158,
+                            "self": 2505.3714593169534,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 120.8636692360842,
-                                    "count": 63457,
-                                    "self": 5.081589715154223,
+                                    "total": 214.25981234506662,
+                                    "count": 87158,
+                                    "self": 8.566666551139974,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 115.78207952092998,
-                                            "count": 62552,
-                                            "self": 115.78207952092998
+                                            "total": 205.69314579392665,
+                                            "count": 85406,
+                                            "self": 205.69314579392665
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9641871369221917,
-                                    "count": 63457,
+                                    "total": 1.7375768309161685,
+                                    "count": 87157,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2240.9100442449935,
-                                            "count": 63457,
+                                            "total": 3774.935332657907,
+                                            "count": 87157,
                                             "is_parallel": true,
-                                            "self": 930.8512729830072,
+                                            "self": 1488.5201336329233,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0028373690001899377,
+                                                            "total": 0.002058512000076007,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008572600008847076,
+                                                            "self": 0.0006784310000966798,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.00198010899930523,
+                                                                    "total": 0.0013800809999793273,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00198010899930523
+                                                                    "self": 0.0013800809999793273
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05323463500008074,
+                                                            "total": 0.10743021899997984,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000578897000195866,
+                                                            "self": 0.0006598019999728422,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004977419994247612,
+                                                                    "total": 0.0005733520000603676,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004977419994247612
+                                                                    "self": 0.0005733520000603676
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05026361300042481,
+                                                                    "total": 0.10393732999989425,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05026361300042481
+                                                                    "self": 0.10393732999989425
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018943830000353046,
+                                                                    "total": 0.0022597350000523875,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003601589996833354,
+                                                                    "self": 0.0004465740000796359,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015342240003519692,
+                                                                            "total": 0.0018131609999727516,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015342240003519692
+                                                                            "self": 0.0018131609999727516
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1310.0587712619863,
-                                                    "count": 63456,
+                                                    "total": 2286.415199024984,
+                                                    "count": 87156,
                                                     "is_parallel": true,
-                                                    "self": 35.32735487098853,
+                                                    "self": 58.757214693991955,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.871370303783806,
-                                                            "count": 63456,
+                                                            "total": 40.65425757292178,
+                                                            "count": 87156,
                                                             "is_parallel": true,
-                                                            "self": 23.871370303783806
+                                                            "self": 40.65425757292178
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1141.192196772,
-                                                            "count": 63456,
+                                                            "total": 1995.1682066750204,
+                                                            "count": 87156,
                                                             "is_parallel": true,
-                                                            "self": 1141.192196772
+                                                            "self": 1995.1682066750204
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 109.66784931521397,
-                                                            "count": 63456,
+                                                            "total": 191.8355200830498,
+                                                            "count": 87156,
                                                             "is_parallel": true,
-                                                            "self": 21.844763893647723,
+                                                            "self": 39.23901168239752,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 87.82308542156625,
-                                                                    "count": 507648,
+                                                                    "total": 152.59650840065228,
+                                                                    "count": 697248,
                                                                     "is_parallel": true,
-                                                                    "self": 87.82308542156625
+                                                                    "self": 152.59650840065228
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 681.7459887060404,
-                            "count": 63457,
-                            "self": 2.961590012997476,
+                            "total": 1052.759976414934,
+                            "count": 87157,
+                            "self": 5.074748490041884,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 113.74007109505419,
-                                    "count": 63457,
-                                    "self": 113.48821886605401,
+                                    "total": 190.53597549689243,
+                                    "count": 87157,
+                                    "self": 190.2910874918923,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.25185222900017834,
+                                            "total": 0.24488800500012076,
                                             "count": 2,
-                                            "self": 0.25185222900017834
+                                            "self": 0.24488800500012076
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 565.0443275979887,
-                                    "count": 459,
-                                    "self": 369.3811039029597,
+                                    "total": 857.1492524279997,
+                                    "count": 623,
+                                    "self": 557.0176884439649,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 195.66322369502905,
-                                            "count": 22767,
-                                            "self": 195.66322369502905
+                                            "total": 300.13156398403487,
+                                            "count": 31134,
+                                            "self": 300.13156398403487
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.020004654303193e-07,
+                    "total": 1.5129999155760743e-06,
                     "count": 1,
-                    "self": 9.020004654303193e-07
+                    "self": 1.5129999155760743e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09782857000027434,
+                    "total": 0.29029868700035877,
                     "count": 1,
-                    "self": 0.0014493360013148049,
+                    "self": 0.00207498400050099,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09637923399895953,
+                            "total": 0.2882237029998578,
                             "count": 1,
-                            "self": 0.09637923399895953
+                            "self": 0.2882237029998578
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499873,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499873.onnx",
-                "reward": -0.9992000460624695,
-                "creation_time": 1691701423.5188596,
+                "steps": 499907,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499907.onnx",
+                "reward": null,
+                "creation_time": 1691752132.9285085,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499873.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499907.pt"
                 ]
             },
             {
-                "steps": 999983,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999983.onnx",
-                "reward": 1.6569999754428864,
-                "creation_time": 1691702607.3323498,
+                "steps": 999994,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999994.onnx",
+                "reward": 1.8325000554323196,
+                "creation_time": 1691753565.578241,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999983.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999994.pt"
                 ]
             },
             {
-                "steps": 1000111,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000111.onnx",
-                "reward": 1.6569999754428864,
-                "creation_time": 1691702607.4399042,
+                "steps": 1365633,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1365633.onnx",
+                "reward": 1.7580000311136246,
+                "creation_time": 1691754661.3311913,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000111.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1365633.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000111,
+            "steps": 1365633,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.6569999754428864,
-            "creation_time": 1691702607.4399042,
+            "reward": 1.7580000311136246,
+            "creation_time": 1691754661.3311913,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000111.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1365633.pt"
             ]
         }
     },