First

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9f55e9c0802cd87f0b8200e03b91e327dab8b14f88301cd923f9f22c1c567e
+oid sha256:22790401a7722a8ce09660ea95f122293a709d10bb07da14ff4730d3632919fa
 size 1420238

Pyramids/Pyramids-1499960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39983b4d527481e953bca52af2e8576d55570d3a7646e6c5ea1b946a6e8c89b
+size 1420238

Pyramids/Pyramids-1499960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed92983a1c472cd13accabd693519b472e9396e498400721133228470b7f8957
+size 8656252

Pyramids/Pyramids-1999931.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22790401a7722a8ce09660ea95f122293a709d10bb07da14ff4730d3632919fa
+size 1420238

Pyramids/Pyramids-1999931.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f08bfb96d5308878420f852763de6b2b0da7da343d9319931c7dd5f6e35678
+size 8656252

Pyramids/Pyramids-2000046.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22790401a7722a8ce09660ea95f122293a709d10bb07da14ff4730d3632919fa
+size 1420238

Pyramids/Pyramids-2000046.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4d5f9f313baee06dd6a063ff12cbca4aa61ec4c7c2afc14fb906b27e85cf1a
+size 8656252

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90d479401461ea0a21d763062a23403dd3de8fca823b3709fb77c8c609f608e
+oid sha256:9f8c9c7e79e73be2a3d7269f78efde0949d1d6c1fa162aebfbb215980aab6513
 size 8655778

Pyramids/events.out.tfevents.1711997790.3588658c0495.17470.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080df99bfd208766480788e912900a78885e45aa1d626fcc6035051cbc9f0222
+size 343080

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": 2000000, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -82,7 +82,7 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

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] 55468 [Flags] 2 [Guid] 2538390594 [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] 55411 [Flags] 2 [Guid] 3197521705 [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  0.091 seconds
+- Completed reload, in  0.090 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -68,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.816079 ms
+UnloadTime: 0.845867 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]: 5654 frames, [32.0 KB-64.0 KB]: 10077 frames, [64.0 KB-128.0 KB]: 3033 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2697 frames, [32.0 KB-64.0 KB]: 10050 frames, [64.0 KB-128.0 KB]: 6020 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18466 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 28 frames, [1.0 MB-2.0 MB]: 18740 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.5 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12856
+  Peak main deferred allocation count 10415
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18764 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 3
-      Peak Allocated memory 29.6 MB
+      Peak Block count 2
+      Peak Allocated memory 25.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18765 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 23.3 MB
+      Peak Allocated memory 21.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18764 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]: 18765 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 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18466 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 53 frames, [1.0 MB-2.0 MB]: 18715 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]: 18764 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 4.7 MB
@@ -291,27 +288,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18765 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]: 18765 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]: 18765 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 27.4 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1711997285436,"processId":6559,"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":1712000308274,"processId":17505,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.4490514397621155,
-            "min": 0.4490514397621155,
-            "max": 1.414385437965393,
+            "value": 0.18705493211746216,
+            "min": 0.16478247940540314,
+            "max": 0.44203102588653564,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 13521.8369140625,
-            "min": 13521.8369140625,
-            "max": 42906.796875,
+            "value": 5605.662109375,
+            "min": 4938.201171875,
+            "max": 12799.0361328125,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 240.1328125,
+            "min": 229.35245901639345,
+            "max": 336.12359550561797,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30737.0,
+            "min": 17589.0,
+            "max": 32323.0,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989915.0,
-            "min": 29935.0,
-            "max": 989915.0,
+            "value": 1979907.0,
+            "min": 1019938.0,
+            "max": 1979907.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989915.0,
-            "min": 29935.0,
-            "max": 989915.0,
+            "value": 1979907.0,
+            "min": 1019938.0,
+            "max": 1979907.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5311144590377808,
-            "min": -0.1967087835073471,
-            "max": 0.6181310415267944,
+            "value": 0.7753037214279175,
+            "min": 0.5842857956886292,
+            "max": 0.7826550602912903,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 147.1186981201172,
-            "min": -47.01340103149414,
-            "max": 170.6041717529297,
+            "value": 234.1417236328125,
+            "min": 112.94467163085938,
+            "max": 234.1417236328125,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.004915765020996332,
-            "min": -0.022140294313430786,
-            "max": 0.7213481068611145,
+            "value": 0.007218698039650917,
+            "min": -0.011078650131821632,
+            "max": 0.023848215118050575,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.3616669178009033,
-            "min": -5.867177963256836,
-            "max": 172.40219116210938,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06767738872371237,
-            "min": 0.06449881695686925,
-            "max": 0.0741522829685848,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9474834421319732,
-            "min": 0.5692847668937268,
-            "max": 1.0704981924888368,
+            "value": 2.180046796798706,
+            "min": -2.0495502948760986,
+            "max": 6.987526893615723,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.016022555058173436,
-            "min": 0.0009761320796690323,
-            "max": 0.02181950573566578,
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7451243954380666,
+            "min": 1.5533956757956935,
+            "max": 1.7542524447695154,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.2243157708144281,
-            "min": 0.011713584956028388,
-            "max": 0.2655850437825874,
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 221.63079822063446,
+            "min": 108.40999849885702,
+            "max": 221.63079822063446,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.299997566699998e-06,
-            "min": 7.299997566699998e-06,
-            "max": 0.0002949910141696625,
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7451243954380666,
+            "min": 1.5533956757956935,
+            "max": 1.7542524447695154,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010219996593379996,
-            "min": 0.00010219996593379996,
-            "max": 0.0037251249582916997,
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 221.63079822063446,
+            "min": 108.40999849885702,
+            "max": 221.63079822063446,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10243330000000002,
-            "min": 0.10243330000000002,
-            "max": 0.1983303375,
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.024534388826761254,
+            "min": 0.024235264870737006,
+            "max": 0.04270739211014271,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4340662000000002,
-            "min": 1.4340662000000002,
-            "max": 2.6109285000000004,
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.1158673809986794,
+            "min": 2.254476272595639,
+            "max": 3.9742181365727447,
             "count": 33
         },
-        "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025308667,
-            "min": 0.00025308667,
-            "max": 0.00983320071625,
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06661360270559921,
+            "min": 0.06401529681924904,
+            "max": 0.07187034715371694,
             "count": 33
         },
-        "Pyramids.Policy.Beta.sum": {
-            "value": 0.0035432133799999997,
-            "min": 0.0035432133799999997,
-            "max": 0.12417665917,
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9325904378783889,
+            "min": 0.5761376713732413,
+            "max": 1.074378561701023,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.01252193283289671,
-            "min": 0.01252193283289671,
-            "max": 0.6707327365875244,
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.016130074523278467,
+            "min": 0.013827307654967978,
+            "max": 0.017788065528859278,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.17530706524848938,
-            "min": 0.17530706524848938,
-            "max": 5.365861892700195,
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.22582104332589853,
+            "min": 0.141306401375914,
+            "max": 0.2668209829328892,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 332.3956043956044,
-            "min": 320.23655913978496,
-            "max": 998.0645161290323,
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 5.160880422596431e-06,
+            "min": 5.160880422596431e-06,
+            "max": 0.00014840945053020002,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30248.0,
-            "min": 17628.0,
-            "max": 32421.0,
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 7.225232591635003e-05,
+            "min": 7.225232591635003e-05,
+            "max": 0.0020269283743574503,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.5565688687066237,
-            "min": -0.934425858480315,
-            "max": 1.6171483657853578,
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10172026071428573,
+            "min": 0.10172026071428573,
+            "max": 0.14946979999999999,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 140.09119818359613,
-            "min": -28.967201612889767,
-            "max": 150.39479801803827,
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4240836500000003,
+            "min": 1.3452282,
+            "max": 2.1564575500000003,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.5565688687066237,
-            "min": -0.934425858480315,
-            "max": 1.6171483657853578,
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00018185404535714294,
+            "min": 0.00018185404535714294,
+            "max": 0.004952033020000001,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 140.09119818359613,
-            "min": -28.967201612889767,
-            "max": 150.39479801803827,
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.002545956635000001,
+            "min": 0.002545956635000001,
+            "max": 0.06763669074499999,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.04314781372848099,
-            "min": 0.04314781372848099,
-            "max": 13.49622757085844,
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.009958143346011639,
+            "min": 0.008901664055883884,
+            "max": 0.012760956771671772,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 3.8833032355632895,
-            "min": 3.8833032355632895,
-            "max": 256.4283238463104,
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.1394140124320984,
+            "min": 0.11117810755968094,
+            "max": 0.1889527291059494,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1711995139",
+        "start_time_seconds": "1711997790",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1711997285"
+        "end_time_seconds": "1712000308"
     },
-    "total": 2146.2897600879996,
+    "total": 2518.126583485,
     "count": 1,
-    "self": 0.5765852339995945,
+    "self": 0.4756415490001018,
     "children": {
         "run_training.setup": {
-            "total": 0.049383508000119036,
+            "total": 0.049040627000067616,
             "count": 1,
-            "self": 0.049383508000119036
+            "self": 0.049040627000067616
         },
         "TrainerController.start_learning": {
-            "total": 2145.663791346,
+            "total": 2517.601901309,
             "count": 1,
-            "self": 1.4266786770226645,
+            "self": 1.4609522070804815,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.0631911109999237,
+                    "total": 2.0384117109997533,
                     "count": 1,
-                    "self": 2.0631911109999237
+                    "self": 2.0384117109997533
                 },
                 "TrainerController.advance": {
-                    "total": 2142.089255012977,
-                    "count": 63857,
-                    "self": 1.3795352539718806,
+                    "total": 2514.013688609919,
+                    "count": 65417,
+                    "self": 1.502925605067503,
                     "children": {
                         "env_step": {
-                            "total": 1521.6886646120256,
-                            "count": 63857,
-                            "self": 1390.6299374330122,
+                            "total": 1874.6336485859447,
+                            "count": 65417,
+                            "self": 1740.1902416718713,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 130.2361156630309,
-                                    "count": 63857,
-                                    "self": 4.704569779032909,
+                                    "total": 133.55975684108216,
+                                    "count": 65417,
+                                    "self": 4.7747069421711785,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 125.53154588399798,
-                                            "count": 62547,
-                                            "self": 125.53154588399798
+                                            "total": 128.78504989891098,
+                                            "count": 62560,
+                                            "self": 128.78504989891098
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.822611515982544,
-                                    "count": 63857,
+                                    "total": 0.8836500729912586,
+                                    "count": 65417,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2140.6659836769927,
-                                            "count": 63857,
+                                            "total": 2512.251911310238,
+                                            "count": 65417,
                                             "is_parallel": true,
-                                            "self": 870.3007710760276,
+                                            "self": 898.011206602202,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0020718289999877015,
+                                                            "total": 0.0022879790003571543,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005796859998099535,
+                                                            "self": 0.0006465400010711164,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001492143000177748,
+                                                                    "total": 0.0016414389992860379,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001492143000177748
+                                                                    "self": 0.0016414389992860379
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04681046200016681,
+                                                            "total": 0.05712476000007882,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006339259998640046,
+                                                            "self": 0.0032920459989327355,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004388180000205466,
+                                                                    "total": 0.0004432969999470515,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004388180000205466
+                                                                    "self": 0.0004432969999470515
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.044125514000143085,
+                                                                    "total": 0.05172769400087418,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.044125514000143085
+                                                                    "self": 0.05172769400087418
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016122040001391724,
+                                                                    "total": 0.001661723000324855,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003375080004843767,
+                                                                    "self": 0.0003732569985004375,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012746959996547957,
+                                                                            "total": 0.0012884660018244176,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012746959996547957
+                                                                            "self": 0.0012884660018244176
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1270.3652126009652,
-                                                    "count": 63856,
+                                                    "total": 1614.240704708036,
+                                                    "count": 65416,
                                                     "is_parallel": true,
-                                                    "self": 33.74786635974647,
+                                                    "self": 34.801910062221395,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 24.500719383115893,
-                                                            "count": 63856,
+                                                            "total": 24.99356799708312,
+                                                            "count": 65416,
                                                             "is_parallel": true,
-                                                            "self": 24.500719383115893
+                                                            "self": 24.99356799708312
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1110.7509613570676,
-                                                            "count": 63856,
+                                                            "total": 1451.0625788657353,
+                                                            "count": 65416,
                                                             "is_parallel": true,
-                                                            "self": 1110.7509613570676
+                                                            "self": 1451.0625788657353
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 101.36566550103521,
-                                                            "count": 63856,
+                                                            "total": 103.38264778299617,
+                                                            "count": 65416,
                                                             "is_parallel": true,
-                                                            "self": 20.387172506917295,
+                                                            "self": 21.307672516118146,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 80.97849299411791,
-                                                                    "count": 510848,
+                                                                    "total": 82.07497526687803,
+                                                                    "count": 523328,
                                                                     "is_parallel": true,
-                                                                    "self": 80.97849299411791
+                                                                    "self": 82.07497526687803
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 619.0210551469795,
-                            "count": 63857,
-                            "self": 2.7393024289472123,
+                            "total": 637.8771144189068,
+                            "count": 65417,
+                            "self": 2.9310192950533747,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 128.09893115103614,
-                                    "count": 63857,
-                                    "self": 127.90310127903649,
+                                    "total": 135.03107008984261,
+                                    "count": 65417,
+                                    "self": 134.81534168884173,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.19582987199964919,
+                                            "total": 0.21572840100088797,
                                             "count": 2,
-                                            "self": 0.19582987199964919
+                                            "self": 0.21572840100088797
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 488.18282156699615,
-                                    "count": 458,
-                                    "self": 285.4315209839617,
+                                    "total": 499.9150250340108,
+                                    "count": 472,
+                                    "self": 294.54177497197907,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 202.75130058303444,
-                                            "count": 22773,
-                                            "self": 202.75130058303444
+                                            "total": 205.37325006203173,
+                                            "count": 22713,
+                                            "self": 205.37325006203173
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 7.990001904545352e-07,
+                    "total": 8.400002116104588e-07,
                     "count": 1,
-                    "self": 7.990001904545352e-07
+                    "self": 8.400002116104588e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0846657460001552,
+                    "total": 0.08884794100049476,
                     "count": 1,
-                    "self": 0.001354509000066173,
+                    "self": 0.0018642500008354546,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08331123700008902,
+                            "total": 0.0869836909996593,
                             "count": 1,
-                            "self": 0.08331123700008902
+                            "self": 0.0869836909996593
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499953,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499953.onnx",
-                "reward": 0.321199968457222,
-                "creation_time": 1711996127.959128,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499953.pt"
-                ]
-            },
             {
                 "steps": 999981,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-999981.onnx",
@@ -27,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000109.pt"
                 ]
+            },
+            {
+                "steps": 1499960,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499960.onnx",
+                "reward": 1.7243333086371422,
+                "creation_time": 1711999030.9681408,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499960.pt"
+                ]
+            },
+            {
+                "steps": 1999931,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999931.onnx",
+                "reward": 1.663374975323677,
+                "creation_time": 1712000307.7470624,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999931.pt"
+                ]
+            },
+            {
+                "steps": 2000046,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000046.onnx",
+                "reward": 1.6881110933091905,
+                "creation_time": 1712000307.8438072,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2000046.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000109,
+            "steps": 2000046,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.020449973642826,
-            "creation_time": 1711997284.889115,
+            "reward": 1.6881110933091905,
+            "creation_time": 1712000307.8438072,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000109.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2000046.pt"
             ]
         }
     },