First Push from colab

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a265436678a74dd98e75f58e77ed8f3a1774aefcc7ac007d08160e7d908239
-size 1418249
+oid sha256:806faa4c2e170a87df44a7807952e9efcba4184c3242155c5fc11b86925b342c
+size 1420238

Pyramids/Pyramids-1000079.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806faa4c2e170a87df44a7807952e9efcba4184c3242155c5fc11b86925b342c
+size 1420238

Pyramids/Pyramids-1000079.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e96dc4941b4049fb2299951881454c126a2f1a2f1249f933549122b204e877
+size 8655228

Pyramids/Pyramids-499909.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f497d5d6a05dbb857fb3e9f829b42806921db5ab72be94edcb86b3b1758798cd
+size 1420238

Pyramids/Pyramids-499909.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636d180f76893ebee7856d75d714894ce0c615d61888fdd95b26d839c86375b4
+size 8655149

Pyramids/Pyramids-999958.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806faa4c2e170a87df44a7807952e9efcba4184c3242155c5fc11b86925b342c
+size 1420238

Pyramids/Pyramids-999958.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d033c99d8e665454a750324ac1a47451d68020738ee605978e5dd900f08c27b0
+size 8655149

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8c59179aa352e9ae8b36f9a617014302c2d9f7cd740bc45fc09be31159f2be
-size 2995106
+oid sha256:4c522a740089682a0a3c9e8177fb5f2fde8429a7639963138dd2ef907883062b
+size 8654754

Pyramids/events.out.tfevents.1735571125.3f9d4397b052.2609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb5ad16bb125ffe71ce7f7792f09f177dcaac305e491c978cee0b00c01ef016
+size 304516

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -83,7 +83,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55211 [Flags] 2 [Guid] 1988356993 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55310 [Flags] 2 [Guid] 1575907773 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.164 seconds
+- Completed reload, in  0.166 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -68,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.313234 ms
+UnloadTime: 1.253772 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 5 frames, [32.0 KB-64.0 KB]: 33 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4831 frames, [32.0 KB-64.0 KB]: 12251 frames, [64.0 KB-128.0 KB]: 1685 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 39 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18469 frames
   Requested Block Size 1.0 MB
-  Peak Block count 1
-  Peak Allocated memory 0.9 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 10758
+  Peak main deferred allocation count 11429
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      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]: 38 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18767 frames
       Requested Block Size 16.0 MB
-      Peak Block count 2
-      Peak Allocated memory 17.9 MB
+      Peak Block count 3
+      Peak Allocated memory 31.5 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 39 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18768 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.7 MB
+      Peak Allocated memory 22.1 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -242,7 +239,7 @@ PlayerConnection::CleanupMemory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 38 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18767 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]: 39 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18768 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 39 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18469 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.9 MB
+      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]: 38 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18767 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.1 MB
@@ -291,27 +288,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.2 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 39 frames
+      Peak usage frame count: [0-1.0 KB]: 18768 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]: 39 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18768 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]: 39 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18768 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 28.6 KB
+  Peak Allocated memory 29.1 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":1735571061902,"processId":2285,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1735573831943,"processId":2646,"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

@@ -1,68 +1,250 @@
 {
     "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.6373741626739502,
+            "min": 0.6334901452064514,
+            "max": 1.4763880968093872,
+            "count": 33
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 19274.1953125,
+            "min": 18741.171875,
+            "max": 44787.7109375,
+            "count": 33
+        },
+        "Pyramids.Step.mean": {
+            "value": 989998.0,
+            "min": 29952.0,
+            "max": 989998.0,
+            "count": 33
+        },
+        "Pyramids.Step.sum": {
+            "value": 989998.0,
+            "min": 29952.0,
+            "max": 989998.0,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.22272032499313354,
+            "min": -0.10300801694393158,
+            "max": 0.2238330990076065,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 57.46184539794922,
+            "min": -24.824932098388672,
+            "max": 57.46184539794922,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.030431821942329407,
+            "min": -0.030431821942329407,
+            "max": 0.367421418428421,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -7.851409912109375,
+            "min": -7.851409912109375,
+            "max": 87.07887268066406,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06790833482089166,
+            "min": 0.06461895713031537,
+            "max": 0.07365442090082362,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9507166874924832,
+            "min": 0.5155809463057653,
+            "max": 1.0450796839249246,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.011459252276836196,
+            "min": 0.00019462852553086006,
+            "max": 0.011459252276836196,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.16042953187570674,
+            "min": 0.0021409137808394607,
+            "max": 0.16042953187570674,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.3423832668571485e-06,
+            "min": 7.3423832668571485e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010279336573600008,
+            "min": 0.00010279336573600008,
+            "max": 0.0031186870604376997,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10244742857142856,
+            "min": 0.10244742857142856,
+            "max": 0.19838354285714285,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.434264,
+            "min": 1.3886848,
+            "max": 2.3589964000000005,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00025449811428571444,
+            "min": 0.00025449811428571444,
+            "max": 0.00983851593142857,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.003562973600000002,
+            "min": 0.003562973600000002,
+            "max": 0.10397227376999998,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.015257926657795906,
+            "min": 0.01466931402683258,
+            "max": 0.3854671120643616,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.21361097693443298,
+            "min": 0.20537039637565613,
+            "max": 2.698269844055176,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 656.0434782608696,
+            "min": 639.8461538461538,
+            "max": 999.0,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30178.0,
+            "min": 15984.0,
+            "max": 33272.0,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 0.9525564793983231,
+            "min": -1.0000000521540642,
+            "max": 0.9525564793983231,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 43.817598052322865,
+            "min": -31.999601677060127,
+            "max": 46.72079824656248,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 0.9525564793983231,
+            "min": -1.0000000521540642,
+            "max": 0.9525564793983231,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 43.817598052322865,
+            "min": -31.999601677060127,
+            "max": 46.72079824656248,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.10305265652942067,
+            "min": 0.10199728273505042,
+            "max": 7.027245636098087,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 4.7404222003533505,
+            "min": 4.385883157607168,
+            "max": 112.43593017756939,
+            "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": "1735571051",
+        "start_time_seconds": "1735571123",
         "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1735571061"
+        "end_time_seconds": "1735573831"
     },
-    "total": 10.769565340999975,
+    "total": 2708.087514588,
     "count": 1,
-    "self": 0.5292419899999459,
+    "self": 0.7459083860003375,
     "children": {
         "run_training.setup": {
-            "total": 0.09992372300001762,
+            "total": 0.09459906399990814,
             "count": 1,
-            "self": 0.09992372300001762
+            "self": 0.09459906399990814
         },
         "TrainerController.start_learning": {
-            "total": 10.140399628000011,
+            "total": 2707.247007138,
             "count": 1,
-            "self": 0.0033106920002410334,
+            "self": 2.044462784022471,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.225910644000066,
+                    "total": 3.5026701219999268,
                     "count": 1,
-                    "self": 6.225910644000066
+                    "self": 3.5026701219999268
                 },
                 "TrainerController.advance": {
-                    "total": 3.770205949999763,
-                    "count": 128,
-                    "self": 0.003370775000348658,
+                    "total": 2701.619903483978,
+                    "count": 63226,
+                    "self": 2.0823131560450747,
                     "children": {
                         "env_step": {
-                            "total": 3.527355932999285,
-                            "count": 128,
-                            "self": 3.1783221879992425,
+                            "total": 1734.705533780952,
+                            "count": 63226,
+                            "self": 1594.4621142209135,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 0.3472803750003095,
-                                    "count": 128,
-                                    "self": 0.009836020000307144,
+                                    "total": 139.01794505901626,
+                                    "count": 63226,
+                                    "self": 5.741377828999475,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 0.33744435500000236,
-                                            "count": 128,
-                                            "self": 0.33744435500000236
+                                            "total": 133.27656723001678,
+                                            "count": 62558,
+                                            "self": 133.27656723001678
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.0017533699997329677,
-                                    "count": 128,
+                                    "total": 1.2254745010221768,
+                                    "count": 63226,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 9.85096235900005,
-                                            "count": 128,
+                                            "total": 2701.057886568959,
+                                            "count": 63226,
                                             "is_parallel": true,
-                                            "self": 7.013854168999842,
+                                            "self": 1257.3386714489097,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0040091039999197164,
+                                                            "total": 0.005429410000033386,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0017526120000184164,
+                                                            "self": 0.0009378129999504381,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0022564919999013,
+                                                                    "total": 0.0044915970000829475,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0022564919999013
+                                                                    "self": 0.0044915970000829475
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.09159657199995763,
+                                                            "total": 0.10294719199998781,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007095839999919917,
+                                                            "self": 0.0007856630002152087,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005154289999609318,
+                                                                    "total": 0.0005131349998919177,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005154289999609318
+                                                                    "self": 0.0005131349998919177
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.08781419199999618,
+                                                                    "total": 0.09750259599991296,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.08781419199999618
+                                                                    "self": 0.09750259599991296
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002557367000008526,
+                                                                    "total": 0.004145797999967726,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005544010000448907,
+                                                                    "self": 0.000423678000174732,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.002002965999963635,
+                                                                            "total": 0.0037221199997929943,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.002002965999963635
+                                                                            "self": 0.0037221199997929943
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2.837108190000208,
-                                                    "count": 127,
+                                                    "total": 1443.7192151200493,
+                                                    "count": 63225,
                                                     "is_parallel": true,
-                                                    "self": 0.08459244600169313,
+                                                    "self": 43.96181901400928,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.053658811000104834,
-                                                            "count": 127,
+                                                            "total": 27.932565640043663,
+                                                            "count": 63225,
                                                             "is_parallel": true,
-                                                            "self": 0.053658811000104834
+                                                            "self": 27.932565640043663
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2.4669192869990866,
-                                                            "count": 127,
+                                                            "total": 1250.817062214013,
+                                                            "count": 63225,
                                                             "is_parallel": true,
-                                                            "self": 2.4669192869990866
+                                                            "self": 1250.817062214013
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.23193764599932365,
-                                                            "count": 127,
+                                                            "total": 121.0077682519834,
+                                                            "count": 63225,
                                                             "is_parallel": true,
-                                                            "self": 0.04699129600135166,
+                                                            "self": 25.852461573077107,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.184946349997972,
-                                                                    "count": 1016,
+                                                                    "total": 95.1553066789063,
+                                                                    "count": 505800,
                                                                     "is_parallel": true,
-                                                                    "self": 0.184946349997972
+                                                                    "self": 95.1553066789063
                                                                 }
                                                             }
                                                         }
@@ -161,33 +343,52 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 0.2394792420001295,
-                            "count": 128,
-                            "self": 0.0029709060012237387,
+                            "total": 964.8320565469807,
+                            "count": 63226,
+                            "self": 3.608022636974283,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 0.23650833599890575,
-                                    "count": 128,
-                                    "self": 0.23650833599890575
+                                    "total": 149.67713122801115,
+                                    "count": 63226,
+                                    "self": 149.42917199701105,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.24795923100009531,
+                                            "count": 2,
+                                            "self": 0.24795923100009531
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 811.5469026819952,
+                                    "count": 438,
+                                    "self": 347.83861224100326,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 463.70829044099196,
+                                            "count": 22857,
+                                            "self": 463.70829044099196
+                                        }
+                                    }
                                 }
                             }
                         }
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0640000027706265e-06,
+                    "total": 1.216999862663215e-06,
                     "count": 1,
-                    "self": 1.0640000027706265e-06
+                    "self": 1.216999862663215e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.14097127799993814,
+                    "total": 0.07996953099973325,
                     "count": 1,
-                    "self": 0.0014283759999216272,
+                    "self": 0.002366009000070335,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1395429020000165,
+                            "total": 0.07760352199966292,
                             "count": 1,
-                            "self": 0.1395429020000165
+                            "self": 0.07760352199966292
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 2048,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2048.onnx",
-                "reward": null,
-                "creation_time": 1735571061.449191,
+                "steps": 499909,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499909.onnx",
+                "reward": -0.30640006562074024,
+                "creation_time": 1735572396.9867194,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-2048.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499909.pt"
+                ]
+            },
+            {
+                "steps": 999958,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999958.onnx",
+                "reward": 1.2939999848604202,
+                "creation_time": 1735573831.1427343,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999958.pt"
+                ]
+            },
+            {
+                "steps": 1000079,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000079.onnx",
+                "reward": 1.5869999900460243,
+                "creation_time": 1735573831.2342153,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000079.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2048,
+            "steps": 1000079,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1735571061.449191,
+            "reward": 1.5869999900460243,
+            "creation_time": 1735573831.2342153,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-2048.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000079.pt"
             ]
         }
     },