Trained Pyramids agent with PPO + RND

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a94b63c7bbe29c1106ea95e4d24965c6e6cd3b32754493dd411f45ff38188f
+size 1420238

Pyramids/Pyramids-1000009.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a94b63c7bbe29c1106ea95e4d24965c6e6cd3b32754493dd411f45ff38188f
+size 1420238

Pyramids/Pyramids-1000009.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d8d7d3f3f5d2f3cc1c0fa3d5d8a2f5e2503e26085f192651cc6b6ba44128f4
+size 8656079

Pyramids/Pyramids-499883.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c59afb6cfcf161d023c9ddae8cb110d1bf4f8c86310120d8144d9e32e27b9a36
+size 1420238

Pyramids/Pyramids-499883.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53fb72f9d42b857ddc92e6e026aca0197be51e7f1f61243a68b764edd05205cd
+size 8656000

Pyramids/Pyramids-999881.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a94b63c7bbe29c1106ea95e4d24965c6e6cd3b32754493dd411f45ff38188f
+size 1420238

Pyramids/Pyramids-999881.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a3febc7a00461cb308c61528b62b12e2bddd2963d3e0d6dd73cf15b0cd99a1
+size 8656000

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d9aef42240cfcbf1ad936f1aa20fab51469c5567950cfb551c527487bb70db3
+size 8655605

Pyramids/events.out.tfevents.1774349794.da2107841361.6306.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38a59ab8458d54f25c9d17116be32417969b06cc627b9ac06ca46973267d1e1
+size 342696

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- Pyramids
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Pyramids
+---
+
+  # **ppo** Agent playing **Pyramids**
+  This is a trained model of a **ppo** agent playing **Pyramids**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: Tass-k/ppo-Pyramids
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +1 @@
+{"behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple"}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"hidden_units": 64, "num_layers": 3}, "learning_rate": 0.0001}}, "keep_checkpoints": 5, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000}}}

configuration.yaml

@@ -0,0 +1,32 @@
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          hidden_units: 64
+          num_layers: 3
+        learning_rate: 0.0001
+    keep_checkpoints: 5
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000

run_logs/Player-0.log

@@ -0,0 +1,317 @@
+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] 55263 [Flags] 2 [Guid] 342058554 [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
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+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  0.134 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)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - 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?
+ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - 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?
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - 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?
+ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - 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?
+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?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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: 0.992344 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.
+PlayerConnection::CleanupMemory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3708 frames, [32.0 KB-64.0 KB]: 11882 frames, [64.0 KB-128.0 KB]: 3176 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
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      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 10]
+      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 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD mixer thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      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 11]
+      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 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.5 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      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 13]
+      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 0]
+      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 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [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 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      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]: 18468 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 12717
+    [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]: 18766 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 31.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18767 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 22.6 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.7 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18766 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]: 18767 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.7 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 1
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      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]: 18468 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]: 18766 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
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.7 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 18767 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]: 18767 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]: 18767 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 29.2 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1774352007962,"processId":6337,"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

@@ -0,0 +1,398 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.45951950550079346,
+            "min": 0.45951950550079346,
+            "max": 1.3073469400405884,
+            "count": 33
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 13756.17578125,
+            "min": 13756.17578125,
+            "max": 39659.67578125,
+            "count": 33
+        },
+        "Pyramids.Step.mean": {
+            "value": 989997.0,
+            "min": 29901.0,
+            "max": 989997.0,
+            "count": 33
+        },
+        "Pyramids.Step.sum": {
+            "value": 989997.0,
+            "min": 29901.0,
+            "max": 989997.0,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.5230852961540222,
+            "min": -0.09277036786079407,
+            "max": 0.6073257923126221,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 144.89462280273438,
+            "min": -22.635969161987305,
+            "max": 168.83657836914062,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.053420089185237885,
+            "min": -0.0034140017814934254,
+            "max": 0.41429218649864197,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 14.797364234924316,
+            "min": -0.9490925073623657,
+            "max": 98.18724822998047,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06367975641232215,
+            "min": 0.06367975641232215,
+            "max": 0.07449174448118952,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9551963461848323,
+            "min": 0.5796412080492537,
+            "max": 1.062237931531854,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.017143356681229193,
+            "min": 0.0009248526530807243,
+            "max": 0.017237112276447066,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.2571503502184379,
+            "min": 0.01109823183696869,
+            "max": 0.25855668414670596,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.441057519680003e-06,
+            "min": 7.441057519680003e-06,
+            "max": 0.0002948457392180875,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00011161586279520004,
+            "min": 0.00011161586279520004,
+            "max": 0.0036354268881911003,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10248032,
+            "min": 0.10248032,
+            "max": 0.19828191250000002,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.5372048,
+            "min": 1.4779371999999997,
+            "max": 2.6118088999999998,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00025778396800000007,
+            "min": 0.00025778396800000007,
+            "max": 0.00982836305875,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.003866759520000001,
+            "min": 0.003866759520000001,
+            "max": 0.12119970911,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.011454583145678043,
+            "min": 0.011454583145678043,
+            "max": 0.4336065649986267,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.17181874811649323,
+            "min": 0.1609770506620407,
+            "max": 3.4688525199890137,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 363.3375,
+            "min": 320.55913978494624,
+            "max": 990.6206896551724,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29067.0,
+            "min": 16316.0,
+            "max": 32596.0,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.5656197352541819,
+            "min": -0.9258061110070257,
+            "max": 1.6579247090604998,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 126.81519855558872,
+            "min": -30.55160166323185,
+            "max": 154.18699794262648,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.5656197352541819,
+            "min": -0.9258061110070257,
+            "max": 1.6579247090604998,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 126.81519855558872,
+            "min": -30.55160166323185,
+            "max": 154.18699794262648,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.043381846219554175,
+            "min": 0.039163820208012755,
+            "max": 8.770061861066257,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.513929543783888,
+            "min": 3.513929543783888,
+            "max": 149.09105163812637,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1774349792",
+        "python_version": "3.10.12 (main, Mar  3 2026, 11:56:32) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1774352008"
+    },
+    "total": 2215.147890494,
+    "count": 1,
+    "self": 1.253988529000253,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02878663299998152,
+            "count": 1,
+            "self": 0.02878663299998152
+        },
+        "TrainerController.start_learning": {
+            "total": 2213.8651153319997,
+            "count": 1,
+            "self": 1.3933979539451684,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.2693291969999336,
+                    "count": 1,
+                    "self": 3.2693291969999336
+                },
+                "TrainerController.advance": {
+                    "total": 2209.0897225200547,
+                    "count": 63911,
+                    "self": 1.4411164489938528,
+                    "children": {
+                        "env_step": {
+                            "total": 1540.935677703997,
+                            "count": 63911,
+                            "self": 1386.0134546429852,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 154.0728831670417,
+                                    "count": 63911,
+                                    "self": 4.708483322068673,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 149.36439984497304,
+                                            "count": 62555,
+                                            "self": 149.36439984497304
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.849339893970182,
+                                    "count": 63911,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2207.748057136973,
+                                            "count": 63911,
+                                            "is_parallel": true,
+                                            "self": 939.9113298389618,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.005398995000064133,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0032955129998981647,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002103482000165968,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002103482000165968
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.06000990199993339,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006024409999554337,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0005850630000168167,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005850630000168167
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.057077855999978055,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.057077855999978055
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0017445419999830847,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003749849997802812,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0013695570002028035,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0013695570002028035
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1267.836727298011,
+                                                    "count": 63910,
+                                                    "is_parallel": true,
+                                                    "self": 34.39222513399977,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 23.47740528601139,
+                                                            "count": 63910,
+                                                            "is_parallel": true,
+                                                            "self": 23.47740528601139
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1097.6219775779614,
+                                                            "count": 63910,
+                                                            "is_parallel": true,
+                                                            "self": 1097.6219775779614
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 112.34511930003839,
+                                                            "count": 63910,
+                                                            "is_parallel": true,
+                                                            "self": 23.70870833116237,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 88.63641096887602,
+                                                                    "count": 511280,
+                                                                    "is_parallel": true,
+                                                                    "self": 88.63641096887602
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 666.7129283670639,
+                            "count": 63911,
+                            "self": 2.7841519210537626,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 127.34662603900676,
+                                    "count": 63911,
+                                    "self": 127.12780509900642,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.21882094000034158,
+                                            "count": 2,
+                                            "self": 0.21882094000034158
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 536.5821504070034,
+                                    "count": 457,
+                                    "self": 295.7930077620157,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 240.7891426449877,
+                                            "count": 22776,
+                                            "self": 240.7891426449877
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.160000106727239e-07,
+                    "count": 1,
+                    "self": 8.160000106727239e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.11266484499992657,
+                    "count": 1,
+                    "self": 0.001470989000154077,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1111938559997725,
+                            "count": 1,
+                            "self": 0.1111938559997725
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499883,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-499883.onnx",
+                "reward": null,
+                "creation_time": 1774350839.4798694,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-499883.pt"
+                ]
+            },
+            {
+                "steps": 999881,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-999881.onnx",
+                "reward": 1.8700000196695328,
+                "creation_time": 1774352006.662074,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-999881.pt"
+                ]
+            },
+            {
+                "steps": 1000009,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000009.onnx",
+                "reward": 1.8700000196695328,
+                "creation_time": 1774352006.7856073,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-1000009.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000009,
+            "file_path": "results/PyramidsTraining/Pyramids.onnx",
+            "reward": 1.8700000196695328,
+            "creation_time": 1774352006.7856073,
+            "auxillary_file_paths": [
+                "results/PyramidsTraining/Pyramids/Pyramids-1000009.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}