First Push

Pyramids/Pyramids-1499942.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c44502d819f80df595fc4d1b4cf04e9ef416c437faa58dcbc937710a19b7fa
+size 1420238

Pyramids/Pyramids-1499942.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f2c100ae44d8570374256a8d97481b7832ab33740cd54be81b57406cd69439
+size 8656252

Pyramids/Pyramids-1628056.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:662c6c3ee2ce3e6095531dcf8bf07fd4cf3604aa01e72aa96b56d5453aa78b04
+size 701

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2c1cdb0f4b27517df0cf2effd64ed678a7eb3101287f05d73605ed74fe7d5b6
+oid sha256:4ac889efeb8927ddc0090d43de32fe198b52a082a1ebe39e58d13f3ae815f4cc
 size 8655778

Pyramids/events.out.tfevents.1710476388.93e5593018db.14257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63893233a9b808908fa509fd67b7519839bcf40dce4ec555d4a9b749d266db4
+size 218828

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": 3000000, "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: 3000000
     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] 55100 [Flags] 2 [Guid] 1825199938 [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] 55122 [Flags] 2 [Guid] 3500344263 [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  0.101 seconds
+- Completed reload, in  0.155 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: 1.251827 ms
+UnloadTime: 0.865933 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]: 8980 frames, [32.0 KB-64.0 KB]: 8141 frames, [64.0 KB-128.0 KB]: 1640 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2419 frames, [32.0 KB-64.0 KB]: 6753 frames, [64.0 KB-128.0 KB]: 2623 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
@@ -96,11 +93,6 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AUDIO_FMOD mixer thread]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 1]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -131,12 +123,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -149,7 +141,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -176,6 +168,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_AUDIO_Audio Mixer Thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -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]: 18463 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 110 frames, [1.0 MB-2.0 MB]: 11686 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.2 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12225
+  Peak main deferred allocation count 6678
     [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]: 18761 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 11795 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 31.7 MB
+      Peak Block count 2
+      Peak Allocated memory 25.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18762 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 11796 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.9 MB
+      Peak Allocated memory 22.3 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]: 18761 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 11795 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]: 18762 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 11796 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,45 +270,45 @@ 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]: 18463 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 149 frames, [1.0 MB-2.0 MB]: 11647 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]: 18761 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 11795 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.5 MB
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18762 frames
+      Peak usage frame count: [0-1.0 KB]: 11796 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]: 18762 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 11796 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]: 18762 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 11796 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 29.0 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":1710475722947,"processId":2172,"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":1710477946652,"processId":14294,"allocatedMemory":1970134,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10604},{"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.6654035449028015,
-            "min": 0.6198781132698059,
-            "max": 1.4324965476989746,
-            "count": 33
+            "value": 0.27660733461380005,
+            "min": 0.27660733461380005,
+            "max": 0.6970478296279907,
+            "count": 21
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 19738.53125,
-            "min": 18725.27734375,
-            "max": 43456.21484375,
-            "count": 33
+            "value": 8227.408203125,
+            "min": 8227.408203125,
+            "max": 21101.03125,
+            "count": 21
         },
         "Pyramids.Step.mean": {
-            "value": 989993.0,
-            "min": 29952.0,
-            "max": 989993.0,
-            "count": 33
+            "value": 1619896.0,
+            "min": 1019972.0,
+            "max": 1619896.0,
+            "count": 21
         },
         "Pyramids.Step.sum": {
-            "value": 989993.0,
-            "min": 29952.0,
-            "max": 989993.0,
-            "count": 33
+            "value": 1619896.0,
+            "min": 1019972.0,
+            "max": 1619896.0,
+            "count": 21
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.11871465295553207,
-            "min": -0.1126789078116417,
-            "max": 0.12750495970249176,
-            "count": 33
+            "value": 0.592436671257019,
+            "min": 0.17887116968631744,
+            "max": 0.5980270504951477,
+            "count": 21
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 29.67866325378418,
-            "min": -27.155616760253906,
-            "max": 31.23871421813965,
-            "count": 33
+            "value": 169.4368896484375,
+            "min": 38.88249206542969,
+            "max": 169.4368896484375,
+            "count": 21
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.032399341464042664,
-            "min": 0.003081351052969694,
-            "max": 0.7086651921272278,
-            "count": 33
+            "value": 0.010919425636529922,
+            "min": -0.01185104250907898,
+            "max": 0.07567622512578964,
+            "count": 21
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 8.099835395812988,
-            "min": 0.7549310326576233,
-            "max": 167.95364379882812,
-            "count": 33
+            "value": 3.122955799102783,
+            "min": -3.176079273223877,
+            "max": 20.810962677001953,
+            "count": 21
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 304.00943396226415,
+            "min": 304.00943396226415,
+            "max": 704.9761904761905,
+            "count": 21
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 32225.0,
+            "min": 15375.0,
+            "max": 33061.0,
+            "count": 21
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6582433830876395,
+            "min": 0.46615810692310333,
+            "max": 1.6687587479647903,
+            "count": 21
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 175.7737986072898,
+            "min": 20.044798597693443,
+            "max": 175.7737986072898,
+            "count": 21
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6582433830876395,
+            "min": 0.46615810692310333,
+            "max": 1.6687587479647903,
+            "count": 21
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 175.7737986072898,
+            "min": 20.044798597693443,
+            "max": 175.7737986072898,
+            "count": 21
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.02843567615113812,
+            "min": 0.02843567615113812,
+            "max": 0.09740542004366817,
+            "count": 21
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.0141816720206407,
+            "min": 2.240261279977858,
+            "max": 4.188433061877731,
+            "count": 21
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06821755483854629,
-            "min": 0.06369347492094293,
-            "max": 0.07224014179821414,
-            "count": 33
+            "value": 0.06440481870612573,
+            "min": 0.06440481870612573,
+            "max": 0.07214185008771558,
+            "count": 21
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.955045767739648,
-            "min": 0.49766075681565847,
-            "max": 1.0625874550748324,
-            "count": 33
+            "value": 0.9016674618857602,
+            "min": 0.6178666375965501,
+            "max": 1.0821277513157337,
+            "count": 21
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.009722731603168151,
-            "min": 0.00033316030966757965,
-            "max": 0.029824517492252407,
-            "count": 33
+            "value": 0.0158456465358525,
+            "min": 0.007521672538129859,
+            "max": 0.016608913912759385,
+            "count": 21
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.1361182424443541,
-            "min": 0.004664244335346115,
-            "max": 0.20877162244576686,
-            "count": 33
+            "value": 0.221839051501935,
+            "min": 0.0910664204234005,
+            "max": 0.24370129945015712,
+            "count": 21
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.309211849342858e-06,
-            "min": 7.309211849342858e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 0.00013951353920979047,
+            "min": 0.00013951353920979047,
+            "max": 0.00019892394480314075,
+            "count": 21
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010232896589080001,
-            "min": 0.00010232896589080001,
-            "max": 0.0033826619724460997,
-            "count": 33
+            "value": 0.0019531895489370665,
+            "min": 0.0017903155032282668,
+            "max": 0.0027675777774742666,
+            "count": 21
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10243637142857143,
-            "min": 0.10243637142857143,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.14650449523809522,
+            "min": 0.14650449523809522,
+            "max": 0.16630797037037037,
+            "count": 21
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4341092,
-            "min": 1.3691136000000002,
-            "max": 2.5275539000000005,
-            "count": 33
+            "value": 2.0510629333333332,
+            "min": 1.4967717333333335,
+            "max": 2.422525733333334,
+            "count": 21
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002533935057142858,
-            "min": 0.0002533935057142858,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.004655799074285713,
+            "min": 0.004655799074285713,
+            "max": 0.006634166239999999,
+            "count": 21
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.003547509080000001,
-            "min": 0.003547509080000001,
-            "max": 0.11278263461,
-            "count": 33
+            "value": 0.06518118703999999,
+            "min": 0.05970749616,
+            "max": 0.09231032076000001,
+            "count": 21
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.014446069486439228,
-            "min": 0.014446069486439228,
-            "max": 0.6883009076118469,
-            "count": 33
+            "value": 0.008971639908850193,
+            "min": 0.008432705886662006,
+            "max": 0.01435074396431446,
+            "count": 21
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.20224496722221375,
-            "min": 0.20224496722221375,
-            "max": 4.818106174468994,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 711.047619047619,
-            "min": 706.05,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29864.0,
-            "min": 15984.0,
-            "max": 32329.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.6022139226281366,
-            "min": -1.0000000521540642,
-            "max": 0.6022139226281366,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 25.895198673009872,
-            "min": -32.000001668930054,
-            "max": 25.895198673009872,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.6022139226281366,
-            "min": -1.0000000521540642,
-            "max": 0.6022139226281366,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 25.895198673009872,
-            "min": -32.000001668930054,
-            "max": 25.895198673009872,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.1066799313452658,
-            "min": 0.1066799313452658,
-            "max": 15.622168138623238,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 4.587237047846429,
-            "min": 4.424240807886235,
-            "max": 249.9546902179718,
-            "count": 33
+            "value": 0.12560296058654785,
+            "min": 0.11805787682533264,
+            "max": 0.1869449019432068,
+            "count": 21
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 21
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 21
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1710473530",
+        "start_time_seconds": "1710476387",
         "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": "1710475723"
+        "end_time_seconds": "1710477946"
     },
-    "total": 2192.71295035,
+    "total": 1558.879617263,
     "count": 1,
-    "self": 0.594711155999903,
+    "self": 0.6296550729998671,
     "children": {
         "run_training.setup": {
-            "total": 0.05610658500000909,
+            "total": 0.08422484399989116,
             "count": 1,
-            "self": 0.05610658500000909
+            "self": 0.08422484399989116
         },
         "TrainerController.start_learning": {
-            "total": 2192.062132609,
+            "total": 1558.1657373460002,
             "count": 1,
-            "self": 1.4695135829570063,
+            "self": 1.012262123995697,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.0383218329999977,
+                    "total": 2.2892777010001737,
                     "count": 1,
-                    "self": 3.0383218329999977
+                    "self": 2.2892777010001737
                 },
                 "TrainerController.advance": {
-                    "total": 2187.467418628043,
-                    "count": 63226,
-                    "self": 1.5136654030375212,
+                    "total": 1554.8604768780046,
+                    "count": 40547,
+                    "self": 1.0200760621187328,
                     "children": {
                         "env_step": {
-                            "total": 1538.7644160830012,
-                            "count": 63226,
-                            "self": 1396.2548176159912,
+                            "total": 1142.0261885059954,
+                            "count": 40547,
+                            "self": 1051.803102436962,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 141.55793911503753,
-                                    "count": 63226,
-                                    "self": 5.134145834031472,
+                                    "total": 89.596789138031,
+                                    "count": 40547,
+                                    "self": 3.2497139430465722,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 136.42379328100606,
-                                            "count": 62537,
-                                            "self": 136.42379328100606
+                                            "total": 86.34707519498443,
+                                            "count": 39320,
+                                            "self": 86.34707519498443
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9516593519724097,
-                                    "count": 63226,
+                                    "total": 0.6262969310023436,
+                                    "count": 40546,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2186.8228899619703,
-                                            "count": 63226,
+                                            "total": 1554.5629688260428,
+                                            "count": 40546,
                                             "is_parallel": true,
-                                            "self": 923.4372933499669,
+                                            "self": 587.4225106940371,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.009720857999980126,
+                                                            "total": 0.002216930000031425,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004632070000070598,
+                                                            "self": 0.0006426989998544741,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.005088787999909528,
+                                                                    "total": 0.001574231000176951,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.005088787999909528
+                                                                    "self": 0.001574231000176951
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05563899100002345,
+                                                            "total": 0.05006574899971383,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008412480000856704,
+                                                            "self": 0.0006695329998365196,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00047900399999889487,
+                                                                    "total": 0.0004964290001225891,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00047900399999889487
+                                                                    "self": 0.0004964290001225891
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05241736199997149,
+                                                                    "total": 0.04715151199980028,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05241736199997149
+                                                                    "self": 0.04715151199980028
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019013769999673968,
+                                                                    "total": 0.0017482749999544467,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003871120000553674,
+                                                                    "self": 0.0003777639994950732,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015142649999120295,
+                                                                            "total": 0.0013705110004593735,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015142649999120295
+                                                                            "self": 0.0013705110004593735
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1263.3855966120034,
-                                                    "count": 63225,
+                                                    "total": 967.1404581320057,
+                                                    "count": 40545,
                                                     "is_parallel": true,
-                                                    "self": 37.25135674900298,
+                                                    "self": 23.175993409091006,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 26.753710269017347,
-                                                            "count": 63225,
+                                                            "total": 16.720818008942842,
+                                                            "count": 40545,
                                                             "is_parallel": true,
-                                                            "self": 26.753710269017347
+                                                            "self": 16.720818008942842
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1088.415419579995,
-                                                            "count": 63225,
+                                                            "total": 856.9368456759912,
+                                                            "count": 40545,
                                                             "is_parallel": true,
-                                                            "self": 1088.415419579995
+                                                            "self": 856.9368456759912
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 110.96511001398818,
-                                                            "count": 63225,
+                                                            "total": 70.30680103798068,
+                                                            "count": 40545,
                                                             "is_parallel": true,
-                                                            "self": 22.883532576998164,
+                                                            "self": 14.780989722108643,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 88.08157743699002,
-                                                                    "count": 505800,
+                                                                    "total": 55.52581131587203,
+                                                                    "count": 324360,
                                                                     "is_parallel": true,
-                                                                    "self": 88.08157743699002
+                                                                    "self": 55.52581131587203
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 647.1893371420044,
-                            "count": 63226,
-                            "self": 2.780257229003837,
+                            "total": 411.81421230989054,
+                            "count": 40546,
+                            "self": 2.0163928877691433,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 135.16311682500015,
-                                    "count": 63226,
-                                    "self": 134.88140251200008,
+                                    "total": 87.82973507513134,
+                                    "count": 40546,
+                                    "self": 87.69651986713097,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2817143130000659,
-                                            "count": 2,
-                                            "self": 0.2817143130000659
+                                            "total": 0.13321520800036524,
+                                            "count": 1,
+                                            "self": 0.13321520800036524
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 509.24596308800045,
-                                    "count": 440,
-                                    "self": 299.65798846402004,
+                                    "total": 321.96808434699005,
+                                    "count": 296,
+                                    "self": 189.38236025700735,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 209.58797462398041,
-                                            "count": 22794,
-                                            "self": 209.58797462398041
+                                            "total": 132.5857240899827,
+                                            "count": 14277,
+                                            "self": 132.5857240899827
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0230000953015406e-06,
+                    "total": 1.2219998097862117e-06,
                     "count": 1,
-                    "self": 1.0230000953015406e-06
+                    "self": 1.2219998097862117e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08687754199991105,
+                    "total": 0.0037194209999142913,
                     "count": 1,
-                    "self": 0.0013713739999730024,
+                    "self": 2.6368999897385947e-05,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08550616799993804,
+                            "total": 0.0036930520000169054,
                             "count": 1,
-                            "self": 0.08550616799993804
+                            "self": 0.0036930520000169054
                         }
                     }
                 }

run_logs/training_status.json

@@ -27,6 +27,15 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000044.pt"
                 ]
+            },
+            {
+                "steps": 1499942,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499942.onnx",
+                "reward": null,
+                "creation_time": 1710477611.1190155,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499942.pt"
+                ]
             }
         ],
         "final_checkpoint": {