First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c41e7cd62f644623b010a5a8fb3135a8cac438d247a79cc88871fb700a69aca
+oid sha256:57ff550406f1918745d1dbc21237493a90a09f51cedcd55fa3708af2728f20ea
 size 1420238

Pyramids/Pyramids-1000014.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ff550406f1918745d1dbc21237493a90a09f51cedcd55fa3708af2728f20ea
+size 1420238

Pyramids/Pyramids-1000014.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c627aa0453ecf617e3ea20dfae2109a8d9d1b3372cc20e78add7313bb95638
+size 8656252

Pyramids/Pyramids-499916.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df3be26e8bf4c1708603179d4da6695a4b655316e3aa2016c7bee36c31bd857
+size 1420238

Pyramids/Pyramids-499916.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947fca4b6318c9eb327719605d007ee6c37343ce3e290ad89d3f5d165cde0e7a
+size 8656173

Pyramids/Pyramids-999886.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ff550406f1918745d1dbc21237493a90a09f51cedcd55fa3708af2728f20ea
+size 1420238

Pyramids/Pyramids-999886.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e26ed042687e8aae0c3a8c54faef513613bc6f646252f070060f95059a7df39
+size 8656173

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03780332ad32f6600f63832b879ea8e3019face2f884ddf0d2e48516c2de88e3
+oid sha256:78245d54ae1774ab4fd4de98e257bc6c08a66998af22b90a8bc45224c692514a
 size 8655778

Pyramids/events.out.tfevents.1710753241.5a08e3e175c3.41444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7da3f30828a135afa1412a148544b1834174a9b472060c37d576c0207c6c52b
+size 333174

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 4096, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 4096, "learning_rate": 0.0006, "beta": 0.01, "epsilon": 0.2, "lambd": 0.961, "num_epoch": 5, "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": 0.995, "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": 0.995, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "PyramidsTraining", "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

@@ -5,11 +5,11 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 4096
-      learning_rate: 0.0003
+      learning_rate: 0.0006
       beta: 0.01
       epsilon: 0.2
-      lambd: 0.95
-      num_epoch: 3
+      lambd: 0.961
+      num_epoch: 5
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear
@@ -25,7 +25,7 @@ behaviors:
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.99
+        gamma: 0.995
         strength: 1.0
         network_settings:
           normalize: false
@@ -36,7 +36,7 @@ behaviors:
           goal_conditioning_type: hyper
           deterministic: false
       rnd:
-        gamma: 0.99
+        gamma: 0.995
         strength: 0.01
         network_settings:
           normalize: false
@@ -79,11 +79,11 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: PyramidsTraining
   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] 55299 [Flags] 2 [Guid] 3529673556 [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] 55263 [Flags] 2 [Guid] 2861188752 [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  0.100 seconds
+- Completed reload, in  0.096 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: 0.969221 ms
+UnloadTime: 0.847454 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]: 5281 frames, [32.0 KB-64.0 KB]: 11718 frames, [64.0 KB-128.0 KB]: 1769 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1850 frames, [32.0 KB-64.0 KB]: 13752 frames, [64.0 KB-128.0 KB]: 3162 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18466 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 11781
+  Peak main deferred allocation count 12953
     [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]: 18768 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18764 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.5 MB
+      Peak Allocated memory 30.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.2 MB
+      Peak Allocated memory 22.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18764 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]: 18769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18765 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]: 18470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18466 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]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18764 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]: 18769 frames
+      Peak usage frame count: [0-1.0 KB]: 18765 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]: 18769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18765 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]: 18769 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18765 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":1710751767818,"processId":25592,"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":1710755840768,"processId":41483,"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

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.6346911787986755,
-            "min": 0.6211602687835693,
-            "max": 1.5168688297271729,
+            "value": 0.41994068026542664,
+            "min": 0.41994068026542664,
+            "max": 1.551714539527893,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 18776.703125,
-            "min": 18776.703125,
-            "max": 46015.734375,
+            "value": 12497.4345703125,
+            "min": 12497.4345703125,
+            "max": 47072.8125,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989902.0,
+            "value": 989884.0,
             "min": 29952.0,
-            "max": 989902.0,
+            "max": 989884.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989902.0,
+            "value": 989884.0,
             "min": 29952.0,
-            "max": 989902.0,
+            "max": 989884.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.2708768844604492,
-            "min": -0.11069012433290482,
-            "max": 0.32056838274002075,
+            "value": 0.902003824710846,
+            "min": -0.13583017885684967,
+            "max": 0.902003824710846,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 69.344482421875,
-            "min": -26.676319122314453,
-            "max": 82.7066421508789,
+            "value": 255.26708984375,
+            "min": -32.73507308959961,
+            "max": 255.26708984375,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.01171177625656128,
-            "min": 0.0075820740312337875,
-            "max": 0.2591050863265991,
+            "value": 0.017675092443823814,
+            "min": 0.01516564842313528,
+            "max": 0.21135880053043365,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 2.9982147216796875,
-            "min": 1.8955185413360596,
-            "max": 62.44432830810547,
+            "value": 5.00205135345459,
+            "min": 4.049228191375732,
+            "max": 50.937469482421875,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06891627325343766,
-            "min": 0.06644774404135421,
-            "max": 0.0733513823049645,
+            "value": 0.06823321763243127,
+            "min": 0.06724950507674034,
+            "max": 0.07581049061181679,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.48241391277406365,
-            "min": 0.2855553419008006,
-            "max": 0.556907365537211,
+            "value": 0.4776325234270189,
+            "min": 0.281222996790376,
+            "max": 0.5898784818564309,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.010975690661802045,
-            "min": 5.442182266020512e-05,
-            "max": 0.011356777255222635,
+            "value": 0.015233842444805693,
+            "min": 0.0001892465855652302,
+            "max": 0.015233842444805693,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.07682983463261432,
-            "min": 0.00038095275862143585,
-            "max": 0.09085421804178108,
+            "value": 0.10663689711363986,
+            "min": 0.0011354795133913813,
+            "max": 0.10663689711363986,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.777811693142862e-06,
-            "min": 7.777811693142862e-06,
-            "max": 0.00029544960151679995,
+            "value": 1.5817125935257134e-05,
+            "min": 1.5817125935257134e-05,
+            "max": 0.0005908992015167998,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 5.4444681852000035e-05,
-            "min": 5.4444681852000035e-05,
-            "max": 0.0018817650727449998,
+            "value": 0.00011071988154679995,
+            "min": 0.00011071988154679995,
+            "max": 0.0036382206936299,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10259257142857141,
-            "min": 0.10259257142857141,
-            "max": 0.1984832,
+            "value": 0.10263617142857144,
+            "min": 0.10263617142857144,
+            "max": 0.19848319999999997,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 0.7181479999999999,
-            "min": 0.7181479999999999,
-            "max": 1.3480081000000002,
+            "value": 0.7184532000000001,
+            "min": 0.7184532000000001,
+            "max": 1.3958485,
             "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026899788571428586,
-            "min": 0.00026899788571428586,
+            "value": 0.00027335352571428563,
+            "min": 0.00027335352571428563,
             "max": 0.009848471680000002,
             "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0018829852000000011,
-            "min": 0.0018829852000000011,
-            "max": 0.0627327745,
+            "value": 0.0019134746799999995,
+            "min": 0.0019134746799999995,
+            "max": 0.06064637299,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.015360629186034203,
-            "min": 0.015360629186034203,
-            "max": 0.4725477993488312,
+            "value": 0.006166991777718067,
+            "min": 0.006166991777718067,
+            "max": 0.2599059045314789,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.10752440243959427,
-            "min": 0.10752440243959427,
-            "max": 1.8901911973953247,
+            "value": 0.043168943375349045,
+            "min": 0.043168943375349045,
+            "max": 1.0396236181259155,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 582.7407407407408,
-            "min": 542.5818181818182,
+            "value": 330.9,
+            "min": 320.72727272727275,
             "max": 999.0,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31468.0,
+            "value": 33090.0,
             "min": 15984.0,
-            "max": 32113.0,
+            "max": 33090.0,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.0097296022706561,
+            "value": 1.5890819773077964,
             "min": -1.0000000521540642,
-            "max": 1.20985996901989,
+            "max": 1.6110658950426362,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 54.52539852261543,
-            "min": -31.99760165810585,
-            "max": 65.2967986240983,
+            "value": 158.90819773077965,
+            "min": -30.538001716136932,
+            "max": 158.90819773077965,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.0097296022706561,
+            "value": 1.5890819773077964,
             "min": -1.0000000521540642,
-            "max": 1.20985996901989,
+            "max": 1.6110658950426362,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 54.52539852261543,
-            "min": -31.99760165810585,
-            "max": 65.2967986240983,
+            "value": 158.90819773077965,
+            "min": -30.538001716136932,
+            "max": 158.90819773077965,
             "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.09188403097828592,
-            "min": 0.08756082651858119,
-            "max": 9.757081017829478,
+            "value": 0.021870249616877117,
+            "min": 0.021870249616877117,
+            "max": 7.622059701476246,
             "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 4.961737672827439,
-            "min": 4.494514025631361,
-            "max": 156.11329628527164,
+            "value": 2.1870249616877118,
+            "min": 1.9785366261785384,
+            "max": 121.95295522361994,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1710749497",
+        "start_time_seconds": "1710753241",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=PyramidsTraining --no-graphics --force",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1710751767"
+        "end_time_seconds": "1710755840"
     },
-    "total": 2270.5077133840005,
+    "total": 2599.790075875,
     "count": 1,
-    "self": 0.4773836390022552,
+    "self": 0.8725405100012722,
     "children": {
         "run_training.setup": {
-            "total": 0.05596239899932698,
+            "total": 0.05263306199958606,
             "count": 1,
-            "self": 0.05596239899932698
+            "self": 0.05263306199958606
         },
         "TrainerController.start_learning": {
-            "total": 2269.974367345999,
+            "total": 2598.8649023029993,
             "count": 1,
-            "self": 1.796371748936508,
+            "self": 1.5426000491042942,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.1676549799994973,
+                    "total": 2.123081154000829,
                     "count": 1,
-                    "self": 2.1676549799994973
+                    "self": 2.123081154000829
                 },
                 "TrainerController.advance": {
-                    "total": 2265.9159335370614,
-                    "count": 63259,
-                    "self": 1.8669520529210786,
+                    "total": 2595.0717567448937,
+                    "count": 63930,
+                    "self": 1.5202277659027459,
                     "children": {
                         "env_step": {
-                            "total": 1607.4352779470228,
-                            "count": 63259,
-                            "self": 1448.4985703060865,
+                            "total": 1604.6939653011868,
+                            "count": 63930,
+                            "self": 1464.4834829431948,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 157.82156543390556,
-                                    "count": 63259,
-                                    "self": 5.451089831021818,
+                                    "total": 139.27501445393136,
+                                    "count": 63930,
+                                    "self": 4.9969301359051315,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 152.37047560288374,
-                                            "count": 62561,
-                                            "self": 152.37047560288374
+                                            "total": 134.27808431802623,
+                                            "count": 62549,
+                                            "self": 134.27808431802623
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.115142207030658,
-                                    "count": 63259,
+                                    "total": 0.9354679040607152,
+                                    "count": 63930,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2264.0568844509116,
-                                            "count": 63259,
+                                            "total": 2593.2434086469657,
+                                            "count": 63930,
                                             "is_parallel": true,
-                                            "self": 958.2511026848724,
+                                            "self": 1258.1205575938802,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0023825090001992066,
+                                                            "total": 0.0022402710001188098,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008304350021717255,
+                                                            "self": 0.0006676819994027028,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015520739980274811,
+                                                                    "total": 0.001572589000716107,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015520739980274811
+                                                                    "self": 0.001572589000716107
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06050894899999548,
+                                                            "total": 0.059136515999853145,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000726043998838577,
+                                                            "self": 0.0007317520012293244,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005277600002955296,
+                                                                    "total": 0.0005336119993444299,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005277600002955296
+                                                                    "self": 0.0005336119993444299
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05728783100039436,
+                                                                    "total": 0.05592021200027375,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05728783100039436
+                                                                    "self": 0.05592021200027375
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001967314000467013,
+                                                                    "total": 0.0019509399990056409,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004527790006250143,
+                                                                    "self": 0.0004174999958195258,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015145349998419988,
+                                                                            "total": 0.001533440003186115,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015145349998419988
+                                                                            "self": 0.001533440003186115
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1305.8057817660392,
-                                                    "count": 63258,
+                                                    "total": 1335.1228510530855,
+                                                    "count": 63929,
                                                     "is_parallel": true,
-                                                    "self": 38.43407483603278,
+                                                    "self": 36.146047124886536,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 26.412382864014035,
-                                                            "count": 63258,
+                                                            "total": 25.554368457811506,
+                                                            "count": 63929,
                                                             "is_parallel": true,
-                                                            "self": 26.412382864014035
+                                                            "self": 25.554368457811506
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1128.7796512420919,
-                                                            "count": 63258,
+                                                            "total": 1165.8202195499944,
+                                                            "count": 63929,
                                                             "is_parallel": true,
-                                                            "self": 1128.7796512420919
+                                                            "self": 1165.8202195499944
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 112.17967282390055,
-                                                            "count": 63258,
+                                                            "total": 107.60221592039306,
+                                                            "count": 63929,
                                                             "is_parallel": true,
-                                                            "self": 23.945960836868835,
+                                                            "self": 22.09969272111448,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 88.23371198703171,
-                                                                    "count": 506064,
+                                                                    "total": 85.50252319927858,
+                                                                    "count": 511432,
                                                                     "is_parallel": true,
-                                                                    "self": 88.23371198703171
+                                                                    "self": 85.50252319927858
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 656.6137035371175,
-                            "count": 63259,
-                            "self": 3.3868490900686083,
+                            "total": 988.8575636778041,
+                            "count": 63930,
+                            "self": 2.8985726268674625,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 134.71623574305977,
-                                    "count": 63259,
-                                    "self": 134.4942529400596,
+                                    "total": 133.4653514649217,
+                                    "count": 63930,
+                                    "self": 133.2155993949218,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2219828030001736,
+                                            "total": 0.24975206999988586,
                                             "count": 2,
-                                            "self": 0.2219828030001736
+                                            "self": 0.24975206999988586
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 518.5106187039892,
-                                    "count": 231,
-                                    "self": 303.3262649149883,
+                                    "total": 852.493639586015,
+                                    "count": 233,
+                                    "self": 498.28564872619427,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 215.18435378900085,
-                                            "count": 23094,
-                                            "self": 215.18435378900085
+                                            "total": 354.2079908598207,
+                                            "count": 38495,
+                                            "self": 354.2079908598207
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.047999830916524e-06,
+                    "total": 1.2920008884975687e-06,
                     "count": 1,
-                    "self": 1.047999830916524e-06
+                    "self": 1.2920008884975687e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09440603200164333,
+                    "total": 0.12746306299959542,
                     "count": 1,
-                    "self": 0.001561720000609057,
+                    "self": 0.0026267180001013912,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09284431200103427,
+                            "total": 0.12483634499949403,
                             "count": 1,
-                            "self": 0.09284431200103427
+                            "self": 0.12483634499949403
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499915,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499915.onnx",
-                "reward": -0.999800056219101,
-                "creation_time": 1710750589.1238878,
+                "steps": 499916,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-499916.onnx",
+                "reward": 1.415999948978424,
+                "creation_time": 1710754433.9289913,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499915.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-499916.pt"
                 ]
             },
             {
-                "steps": 999920,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999920.onnx",
-                "reward": null,
-                "creation_time": 1710751767.2828908,
+                "steps": 999886,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-999886.onnx",
+                "reward": 1.7930000027020772,
+                "creation_time": 1710755839.8558712,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999920.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-999886.pt"
                 ]
             },
             {
-                "steps": 1000048,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000048.onnx",
-                "reward": null,
-                "creation_time": 1710751767.388921,
+                "steps": 1000014,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000014.onnx",
+                "reward": 1.7930000027020772,
+                "creation_time": 1710755840.0015442,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000048.pt"
+                    "results/PyramidsTraining/Pyramids/Pyramids-1000014.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000048,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1710751767.388921,
+            "steps": 1000014,
+            "file_path": "results/PyramidsTraining/Pyramids.onnx",
+            "reward": 1.7930000027020772,
+            "creation_time": 1710755840.0015442,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000048.pt"
+                "results/PyramidsTraining/Pyramids/Pyramids-1000014.pt"
             ]
         }
     },