Initial commit of Pyramids training results

Pyramids Training/Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58379aa0020495e97ca6413d0491ffd29299297fac19259cfe76a76cc2ebec4f
+size 1420238

Pyramids Training/Pyramids/Pyramids-1499929.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58379aa0020495e97ca6413d0491ffd29299297fac19259cfe76a76cc2ebec4f
+size 1420238

Pyramids Training/Pyramids/Pyramids-1499929.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a652fdd791dad9b99327cca42c48343c8b327cc37166d4e715c3f60fc873c7
+size 8656252

Pyramids Training/Pyramids/Pyramids-1500057.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58379aa0020495e97ca6413d0491ffd29299297fac19259cfe76a76cc2ebec4f
+size 1420238

Pyramids Training/Pyramids/Pyramids-1500057.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df561f7127d9d68aa3b3365d24573116884eba1c3337f94006c35238d19b84a6
+size 8656252

Pyramids Training/Pyramids/Pyramids-499993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5e279b06c1a627829610833c34fc1b4c1138c7b89c7aa6ab8482b58aba84c0
+size 1420238

Pyramids Training/Pyramids/Pyramids-499993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0dbf7384c3210ee2ff3136dd444326dc5a10bc49fb463b6cb58761da74f2f45
+size 8656173

Pyramids Training/Pyramids/Pyramids-999946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0c6f24ec18f120c9fc6047a6a9ad7ca7f1cba40130745fec185595abfb038d
+size 1420238

Pyramids Training/Pyramids/Pyramids-999946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c850045bf36dce00bb12fddc3b3a02044dc4c2508d59f19843ca93b6c6732b3
+size 8656173

Pyramids Training/Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8bc164f801fc8b795f3c1a5f017c40824b075505c64dde7a23932625a1578c
+size 8655778

Pyramids Training/Pyramids/events.out.tfevents.1730961223.ali.23833.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10cb573a13cb409de04aebb5a8319762a5d8aa39831e78a72e8ca0e73d629562
+size 462578

Pyramids Training/configuration.yaml

@@ -0,0 +1,92 @@
+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: ./Pyramids
+  env_args: null
+  base_port: 6005
+  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

Pyramids Training/run_logs/Player-0.log

@@ -0,0 +1,319 @@
+Mono path[0] = '/root/hfRL/ml/pyramids_v2/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/root/hfRL/ml/pyramids_v2/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 2 interfaces on host : 0) 10.255.255.254 1) 172.21.198.209
+Multi-casting "[IP] 10.255.255.254 [Port] 55451 [Flags] 2 [Guid] 1272506278 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.21.198.209) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /root/hfRL/ml/pyramids_v2/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
+Begin MonoManager ReloadAssembly
+- Completed reload, in  2.208 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: 2.788000 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 3 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]: 4769 frames, [32.0 KB-64.0 KB]: 16847 frames, [64.0 KB-128.0 KB]: 6528 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_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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_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 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      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_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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_AUDIO_FMOD PulseAudio Mixer]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [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_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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] x 6
+      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_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      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_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_EnlightenWorker] x 3
+      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]: 27846 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 11811
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.8 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 28144 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 30.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 28145 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 26.7 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 1.8 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 28144 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]: 28145 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 1.8 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 27846 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]: 28144 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 6.0 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 1.8 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 28145 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]: 28145 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]: 28145 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 31.1 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1730965705172,"processId":23882,"allocatedMemory":2090237,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":128012},{"Thread":34600},{"Manager":13391},{"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":3372},{"DynamicArray":30868},{"HashMap":7680},{"Utility":3400},{"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}]}

Pyramids Training/run_logs/timers.json

@@ -0,0 +1,398 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.19532400369644165,
+            "min": 0.19176672399044037,
+            "max": 1.431990623474121,
+            "count": 50
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 5875.34619140625,
+            "min": 5722.31884765625,
+            "max": 43440.8671875,
+            "count": 50
+        },
+        "Pyramids.Step.mean": {
+            "value": 1499929.0,
+            "min": 29952.0,
+            "max": 1499929.0,
+            "count": 50
+        },
+        "Pyramids.Step.sum": {
+            "value": 1499929.0,
+            "min": 29952.0,
+            "max": 1499929.0,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.8025957942008972,
+            "min": -0.09869258105754852,
+            "max": 0.8025957942008972,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 243.98912048339844,
+            "min": -23.982297897338867,
+            "max": 243.98912048339844,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.010153330862522125,
+            "min": -0.007649863604456186,
+            "max": 0.5776370763778687,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 3.0866127014160156,
+            "min": -2.1419618129730225,
+            "max": 136.89999389648438,
+            "count": 50
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06757387201845025,
+            "min": 0.06485950882086486,
+            "max": 0.07370327567884065,
+            "count": 50
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0136080802767538,
+            "min": 0.5089080015440932,
+            "max": 1.0536614030327958,
+            "count": 50
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.014148789550138947,
+            "min": 0.0008208262323227651,
+            "max": 0.016990357592045813,
+            "count": 50
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.2122318432520842,
+            "min": 0.009849914787873181,
+            "max": 0.2391615626014148,
+            "count": 50
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 2.9594723468755577e-06,
+            "min": 2.9594723468755577e-06,
+            "max": 0.00029676708679192377,
+            "count": 50
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 4.4392085203133365e-05,
+            "min": 4.4392085203133365e-05,
+            "max": 0.0038223127258957997,
+            "count": 50
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10098645777777779,
+            "min": 0.10098645777777779,
+            "max": 0.19892236190476195,
+            "count": 50
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.514796866666667,
+            "min": 1.3924565333333336,
+            "max": 2.6741041999999995,
+            "count": 50
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00010854713200000004,
+            "min": 0.00010854713200000004,
+            "max": 0.009892343954285714,
+            "count": 50
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0016282069800000007,
+            "min": 0.0016282069800000007,
+            "max": 0.12742300957999997,
+            "count": 50
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.012307985685765743,
+            "min": 0.012307985685765743,
+            "max": 0.6702824831008911,
+            "count": 50
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.18461978435516357,
+            "min": 0.17698363959789276,
+            "max": 4.691977500915527,
+            "count": 50
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 229.97619047619048,
+            "min": 229.45736434108528,
+            "max": 999.0,
+            "count": 50
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28977.0,
+            "min": 15984.0,
+            "max": 32550.0,
+            "count": 50
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.770023800432682,
+            "min": -1.0000000521540642,
+            "max": 1.770023800432682,
+            "count": 50
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 223.02299885451794,
+            "min": -29.86300168186426,
+            "max": 226.51599816977978,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.770023800432682,
+            "min": -1.0000000521540642,
+            "max": 1.770023800432682,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 223.02299885451794,
+            "min": -29.86300168186426,
+            "max": 226.51599816977978,
+            "count": 50
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.029647420209094267,
+            "min": 0.029647420209094267,
+            "max": 12.51437996700406,
+            "count": 50
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.735574946345878,
+            "min": 3.735574946345878,
+            "max": 200.23007947206497,
+            "count": 50
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1730961208",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
+        "command_line_arguments": "/root/miniconda3/envs/pyramids2/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./Pyramids --run-id=Pyramids Training --results-dir=./results --no-graphics --base-port=6005",
+        "mlagents_version": "1.1.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1730965705"
+    },
+    "total": 4224.695456683,
+    "count": 1,
+    "self": 1.1911924490004822,
+    "children": {
+        "run_training.setup": {
+            "total": 0.06859295999993265,
+            "count": 1,
+            "self": 0.06859295999993265
+        },
+        "TrainerController.start_learning": {
+            "total": 4223.435671274,
+            "count": 1,
+            "self": 2.1002487250025297,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 20.490043730999787,
+                    "count": 1,
+                    "self": 20.490043730999787
+                },
+                "TrainerController.advance": {
+                    "total": 4200.702905977998,
+                    "count": 96801,
+                    "self": 2.142794361028791,
+                    "children": {
+                        "env_step": {
+                            "total": 2522.388875197892,
+                            "count": 96801,
+                            "self": 2093.626724642923,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 427.35822932516476,
+                                    "count": 96801,
+                                    "self": 7.878471373166576,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 419.4797579519982,
+                                            "count": 93815,
+                                            "self": 419.4797579519982
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.4039212298043822,
+                                    "count": 96801,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4218.280266425885,
+                                            "count": 96801,
+                                            "is_parallel": true,
+                                            "self": 2282.143642674496,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.007872373999816773,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.005579013999977178,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002293359999839595,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002293359999839595
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.07592517500006579,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008168600002136372,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0009182529997815436,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0009182529997815436
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.07289752699989549,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.07289752699989549
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0012925350001751212,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003405869997550326,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0009519480004200886,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0009519480004200886
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1936.1366237513894,
+                                                    "count": 96800,
+                                                    "is_parallel": true,
+                                                    "self": 29.34667341645263,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 23.169359972988786,
+                                                            "count": 96800,
+                                                            "is_parallel": true,
+                                                            "self": 23.169359972988786
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1786.8466746432405,
+                                                            "count": 96800,
+                                                            "is_parallel": true,
+                                                            "self": 1786.8466746432405
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 96.77391571870749,
+                                                            "count": 96800,
+                                                            "is_parallel": true,
+                                                            "self": 23.00106582061926,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 73.77284989808823,
+                                                                    "count": 774400,
+                                                                    "is_parallel": true,
+                                                                    "self": 73.77284989808823
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1676.171236419077,
+                            "count": 96801,
+                            "self": 4.071546576061792,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 246.64640003601926,
+                                    "count": 96801,
+                                    "self": 245.84998928601817,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.7964107500010869,
+                                            "count": 3,
+                                            "self": 0.7964107500010869
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1425.453289806996,
+                                    "count": 690,
+                                    "self": 550.4882944030546,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 874.9649954039414,
+                                            "count": 34224,
+                                            "self": 874.9649954039414
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.429997251369059e-07,
+                    "count": 1,
+                    "self": 8.429997251369059e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.14247199700002966,
+                    "count": 1,
+                    "self": 0.0013185789994167862,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14115341800061287,
+                            "count": 1,
+                            "self": 0.14115341800061287
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

Pyramids Training/run_logs/training_status.json

@@ -0,0 +1,56 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499993,
+                "file_path": "./results/Pyramids Training/Pyramids/Pyramids-499993.onnx",
+                "reward": null,
+                "creation_time": 1730962729.933057,
+                "auxillary_file_paths": [
+                    "./results/Pyramids Training/Pyramids/Pyramids-499993.pt"
+                ]
+            },
+            {
+                "steps": 999946,
+                "file_path": "./results/Pyramids Training/Pyramids/Pyramids-999946.onnx",
+                "reward": 1.7309999763965607,
+                "creation_time": 1730964180.7932913,
+                "auxillary_file_paths": [
+                    "./results/Pyramids Training/Pyramids/Pyramids-999946.pt"
+                ]
+            },
+            {
+                "steps": 1499929,
+                "file_path": "./results/Pyramids Training/Pyramids/Pyramids-1499929.onnx",
+                "reward": null,
+                "creation_time": 1730965704.054896,
+                "auxillary_file_paths": [
+                    "./results/Pyramids Training/Pyramids/Pyramids-1499929.pt"
+                ]
+            },
+            {
+                "steps": 1500057,
+                "file_path": "./results/Pyramids Training/Pyramids/Pyramids-1500057.onnx",
+                "reward": null,
+                "creation_time": 1730965704.213639,
+                "auxillary_file_paths": [
+                    "./results/Pyramids Training/Pyramids/Pyramids-1500057.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1500057,
+            "file_path": "./results/Pyramids Training/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1730965704.213639,
+            "auxillary_file_paths": [
+                "./results/Pyramids Training/Pyramids/Pyramids-1500057.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0",
+        "torch_version": "2.5.1+cu124"
+    }
+}

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: alidenewade/ML-Agents-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": 1500000, "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: 1500000
+    time_horizon: 128
+    summary_freq: 30000

mlagents_output.log

@@ -0,0 +1,135 @@
+
+            ┐  ╖
+        ╓╖╬│╡  ││╬╖╖
+    ╓╖╬│││││┘  ╬│││││╬╖
+ ╖╬│││││╬╜        ╙╬│││││╖╖                               ╗╗╗
+ ╬╬╬╬╖││╦╖        ╖╬││╗╣╣╣╬      ╟╣╣╬    ╟╣╣╣             ╜╜╜  ╟╣╣
+ ╬╬╬╬╬╬╬╬╖│╬╖╖╓╬╪│╓╣╣╣╣╣╣╣╬      ╟╣╣╬    ╟╣╣╣ ╒╣╣╖╗╣╣╣╗   ╣╣╣ ╣╣╣╣╣╣ ╟╣╣╖   ╣╣╣
+ ╬╬╬╬┐  ╙╬╬╬╬│╓╣╣╣╝╜  ╫╣╣╣╬      ╟╣╣╬    ╟╣╣╣ ╟╣╣╣╙ ╙╣╣╣  ╣╣╣ ╙╟╣╣╜╙  ╫╣╣  ╟╣╣
+ ╬╬╬╬┐     ╙╬╬╣╣      ╫╣╣╣╬      ╟╣╣╬    ╟╣╣╣ ╟╣╣╬   ╣╣╣  ╣╣╣  ╟╣╣     ╣╣╣┌╣╣╜
+ ╬╬╬╜       ╬╬╣╣      ╙╝╣╣╬      ╙╣╣╣╗╖╓╗╣╣╣╜ ╟╣╣╬   ╣╣╣  ╣╣╣  ╟╣╣╦╓    ╣╣╣╣╣
+ ╙   ╓╦╖    ╬╬╣╣   ╓╗╗╖            ╙╝╣╣╣╣╝╜   ╘╝╝╜   ╝╝╝  ╝╝╝   ╙╣╣╣    ╟╣╣╣
+   ╩╬╬╬╬╬╬╦╦╬╬╣╣╗╣╣╣╣╣╣╣╝                                             ╫╣╣╣╣
+      ╙╬╬╬╬╬╬╬╣╣╣╣╣╣╝╜
+          ╙╬╬╬╣╣╣╜
+             ╙
+        
+ Version information:
+  ml-agents: 1.1.0,
+  ml-agents-envs: 1.1.0,
+  Communicator API: 1.5.0,
+  PyTorch: 2.5.1+cu124
+[INFO] Connected to Unity environment with package version 2.2.1-exp.1 and communication version 1.5.0
+[INFO] Connected new brain: Pyramids?team=0
+[INFO] Hyperparameters for behavior name 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:	None
+	  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:	None
+	      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:	None
+	      goal_conditioning_type:	hyper
+	      deterministic:	False
+	    learning_rate:	0.0001
+	    encoding_size:	None
+	init_path:	None
+	keep_checkpoints:	5
+	even_checkpoints:	False
+	max_steps:	1500000
+	time_horizon:	128
+	summary_freq:	30000
+	threaded:	False
+	self_play:	None
+	behavioral_cloning:	None
+[INFO] Pyramids. Step: 30000. Time Elapsed: 148.003 s. Mean Reward: -1.000. Std of Reward: 0.000. Training.
+[INFO] Pyramids. Step: 60000. Time Elapsed: 265.467 s. Mean Reward: -0.933. Std of Reward: 0.372. Training.
+[INFO] Pyramids. Step: 90000. Time Elapsed: 367.221 s. Mean Reward: -0.710. Std of Reward: 0.798. Training.
+[INFO] Pyramids. Step: 120000. Time Elapsed: 464.638 s. Mean Reward: -0.776. Std of Reward: 0.720. Training.
+[INFO] Pyramids. Step: 150000. Time Elapsed: 558.278 s. Mean Reward: -0.767. Std of Reward: 0.704. Training.
+[INFO] Pyramids. Step: 180000. Time Elapsed: 647.350 s. Mean Reward: -0.735. Std of Reward: 0.702. Training.
+[INFO] Pyramids. Step: 210000. Time Elapsed: 729.384 s. Mean Reward: -0.734. Std of Reward: 0.718. Training.
+[INFO] Pyramids. Step: 240000. Time Elapsed: 811.080 s. Mean Reward: -0.770. Std of Reward: 0.717. Training.
+[INFO] Pyramids. Step: 270000. Time Elapsed: 892.234 s. Mean Reward: -0.677. Std of Reward: 0.828. Training.
+[INFO] Pyramids. Step: 300000. Time Elapsed: 972.033 s. Mean Reward: -0.623. Std of Reward: 0.880. Training.
+[INFO] Pyramids. Step: 330000. Time Elapsed: 1052.993 s. Mean Reward: -0.547. Std of Reward: 0.933. Training.
+[INFO] Pyramids. Step: 360000. Time Elapsed: 1133.943 s. Mean Reward: -0.255. Std of Reward: 1.081. Training.
+[INFO] Pyramids. Step: 390000. Time Elapsed: 1214.047 s. Mean Reward: 0.361. Std of Reward: 1.218. Training.
+[INFO] Pyramids. Step: 420000. Time Elapsed: 1295.921 s. Mean Reward: 0.438. Std of Reward: 1.226. Training.
+[INFO] Pyramids. Step: 450000. Time Elapsed: 1379.688 s. Mean Reward: 0.412. Std of Reward: 1.220. Training.
+[INFO] Pyramids. Step: 480000. Time Elapsed: 1462.029 s. Mean Reward: 0.791. Std of Reward: 1.133. Training.
+[INFO] Exported ./results/Pyramids Training/Pyramids/Pyramids-499993.onnx
+[INFO] Pyramids. Step: 510000. Time Elapsed: 1548.600 s. Mean Reward: 1.152. Std of Reward: 0.981. Training.
+[INFO] Pyramids. Step: 540000. Time Elapsed: 1633.251 s. Mean Reward: 1.311. Std of Reward: 0.824. Training.
+[INFO] Pyramids. Step: 570000. Time Elapsed: 1721.782 s. Mean Reward: 1.343. Std of Reward: 0.833. Training.
+[INFO] Pyramids. Step: 600000. Time Elapsed: 1805.904 s. Mean Reward: 1.378. Std of Reward: 0.772. Training.
+[INFO] Pyramids. Step: 630000. Time Elapsed: 1893.478 s. Mean Reward: 1.566. Std of Reward: 0.591. Training.
+[INFO] Pyramids. Step: 660000. Time Elapsed: 1977.764 s. Mean Reward: 1.453. Std of Reward: 0.686. Training.
+[INFO] Pyramids. Step: 690000. Time Elapsed: 2066.482 s. Mean Reward: 1.632. Std of Reward: 0.319. Training.
+[INFO] Pyramids. Step: 720000. Time Elapsed: 2151.482 s. Mean Reward: 1.549. Std of Reward: 0.660. Training.
+[INFO] Pyramids. Step: 750000. Time Elapsed: 2240.531 s. Mean Reward: 1.592. Std of Reward: 0.536. Training.
+[INFO] Pyramids. Step: 780000. Time Elapsed: 2328.085 s. Mean Reward: 1.706. Std of Reward: 0.193. Training.
+[INFO] Pyramids. Step: 810000. Time Elapsed: 2411.292 s. Mean Reward: 1.578. Std of Reward: 0.580. Training.
+[INFO] Pyramids. Step: 840000. Time Elapsed: 2501.359 s. Mean Reward: 1.682. Std of Reward: 0.335. Training.
+[INFO] Pyramids. Step: 870000. Time Elapsed: 2586.919 s. Mean Reward: 1.659. Std of Reward: 0.333. Training.
+[INFO] Pyramids. Step: 900000. Time Elapsed: 2680.870 s. Mean Reward: 1.629. Std of Reward: 0.434. Training.
+[INFO] Pyramids. Step: 930000. Time Elapsed: 2767.200 s. Mean Reward: 1.597. Std of Reward: 0.560. Training.
+[INFO] Pyramids. Step: 960000. Time Elapsed: 2857.335 s. Mean Reward: 1.724. Std of Reward: 0.166. Training.
+[INFO] Pyramids. Step: 990000. Time Elapsed: 2941.618 s. Mean Reward: 1.619. Std of Reward: 0.553. Training.
+[INFO] Exported ./results/Pyramids Training/Pyramids/Pyramids-999946.onnx
+[INFO] Pyramids. Step: 1020000. Time Elapsed: 3028.674 s. Mean Reward: 1.678. Std of Reward: 0.411. Training.
+[INFO] Pyramids. Step: 1050000. Time Elapsed: 3118.122 s. Mean Reward: 1.692. Std of Reward: 0.402. Training.
+[INFO] Pyramids. Step: 1080000. Time Elapsed: 3216.680 s. Mean Reward: 1.727. Std of Reward: 0.183. Training.
+[INFO] Pyramids. Step: 1110000. Time Elapsed: 3311.014 s. Mean Reward: 1.661. Std of Reward: 0.489. Training.
+[INFO] Pyramids. Step: 1140000. Time Elapsed: 3403.759 s. Mean Reward: 1.660. Std of Reward: 0.528. Training.
+[INFO] Pyramids. Step: 1170000. Time Elapsed: 3502.028 s. Mean Reward: 1.663. Std of Reward: 0.472. Training.
+[INFO] Pyramids. Step: 1200000. Time Elapsed: 3593.599 s. Mean Reward: 1.724. Std of Reward: 0.368. Training.
+[INFO] Pyramids. Step: 1230000. Time Elapsed: 3696.908 s. Mean Reward: 1.726. Std of Reward: 0.294. Training.
+[INFO] Pyramids. Step: 1260000. Time Elapsed: 3794.103 s. Mean Reward: 1.698. Std of Reward: 0.393. Training.
+[INFO] Pyramids. Step: 1290000. Time Elapsed: 3880.079 s. Mean Reward: 1.725. Std of Reward: 0.296. Training.
+[INFO] Pyramids. Step: 1320000. Time Elapsed: 3962.680 s. Mean Reward: 1.721. Std of Reward: 0.297. Training.
+[INFO] Pyramids. Step: 1350000. Time Elapsed: 4045.175 s. Mean Reward: 1.770. Std of Reward: 0.140. Training.
+[INFO] Pyramids. Step: 1380000. Time Elapsed: 4137.379 s. Mean Reward: 1.735. Std of Reward: 0.287. Training.
+[INFO] Pyramids. Step: 1410000. Time Elapsed: 4225.323 s. Mean Reward: 1.680. Std of Reward: 0.395. Training.
+[INFO] Pyramids. Step: 1440000. Time Elapsed: 4312.635 s. Mean Reward: 1.731. Std of Reward: 0.297. Training.
+[INFO] Pyramids. Step: 1470000. Time Elapsed: 4398.072 s. Mean Reward: 1.720. Std of Reward: 0.380. Training.
+[INFO] Pyramids. Step: 1500000. Time Elapsed: 4495.374 s. Mean Reward: 1.770. Std of Reward: 0.128. Training.
+[INFO] Exported ./results/Pyramids Training/Pyramids/Pyramids-1499929.onnx
+[INFO] Exported ./results/Pyramids Training/Pyramids/Pyramids-1500057.onnx
+[INFO] Copied ./results/Pyramids Training/Pyramids/Pyramids-1500057.onnx to ./results/Pyramids Training/Pyramids.onnx.