First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9878e5402aea78e0b221e88c6fea2d51223e07e761947cddf5d4b4dae7828a
+oid sha256:31d7e400be7ae3ff04c6eef6b676ce21819cc39d184b99b4bf51f0e1985c86df
 size 1420238

Pyramids/Pyramids-1499946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d7e400be7ae3ff04c6eef6b676ce21819cc39d184b99b4bf51f0e1985c86df
+size 1420238

Pyramids/Pyramids-1499946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65358d78af9061326896e401145b137763841427f9b69da5ef598bddb9e6ef76
+size 8656252

Pyramids/Pyramids-1500074.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d7e400be7ae3ff04c6eef6b676ce21819cc39d184b99b4bf51f0e1985c86df
+size 1420238

Pyramids/Pyramids-1500074.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39fc12f22b9bc9b1e790714ace7e0560764f4dd97e00e995ab1f0da081e327d9
+size 8656252

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc51c5e6e65bd98ec83dbdc8322d70cd756b09d32f207fb5d4672638d4c19b0
+oid sha256:ef0f8bff4b0e9864efb47ade2fdb21295d70305a00bf790cba04a69f01a2a216
 size 8655778

Pyramids/events.out.tfevents.1717186220.6d7e2a8db8d8.19685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5050f7b3c5e3e426c2acfd211b51ab1e3af36a2a32d9237340237244f7a0b7
+size 1422

Pyramids/events.out.tfevents.1717186257.6d7e2a8db8d8.19903.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c79290a67d6ebede2b0a547d8a0855cb4ff420320b9dc348508846a4d1be121
+size 158676

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": 1500000, "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: 1500000
     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] 55355 [Flags] 2 [Guid] 2262087060 [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] 55326 [Flags] 2 [Guid] 2628174267 [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  0.147 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: 1.154557 ms
+UnloadTime: 0.833452 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]: 4825 frames, [32.0 KB-64.0 KB]: 10739 frames, [64.0 KB-128.0 KB]: 3200 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1050 frames, [32.0 KB-64.0 KB]: 5620 frames, [64.0 KB-128.0 KB]: 2718 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
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -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]: 31 frames, [1.0 MB-2.0 MB]: 9358 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11475
+  Peak main deferred allocation count 7324
     [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]: 9388 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 30.7 MB
+      Peak Block count 2
+      Peak Allocated memory 24.2 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]: 9389 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.1 MB
+      Peak Allocated memory 22.9 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]: 9388 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]: 9389 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]: 18466 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 69 frames, [1.0 MB-2.0 MB]: 9320 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]: 9388 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.1 MB
+      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]: 18765 frames
+      Peak usage frame count: [0-1.0 KB]: 9389 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]: 9389 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]: 9389 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.1 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":1717185954295,"processId":9167,"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":1717187516256,"processId":19932,"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.5245121717453003,
-            "min": 0.5245121717453003,
-            "max": 1.4683809280395508,
-            "count": 33
+            "value": 0.3748374879360199,
+            "min": 0.3748374879360199,
+            "max": 0.5130709409713745,
+            "count": 17
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 15676.619140625,
-            "min": 15676.619140625,
-            "max": 44544.8046875,
-            "count": 33
+            "value": 11191.1484375,
+            "min": 10753.966796875,
+            "max": 15011.27734375,
+            "count": 17
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 253.2136752136752,
+            "min": 253.2136752136752,
+            "max": 367.75581395348837,
+            "count": 17
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29626.0,
+            "min": 15649.0,
+            "max": 31913.0,
+            "count": 17
         },
         "Pyramids.Step.mean": {
-            "value": 989974.0,
-            "min": 29952.0,
-            "max": 989974.0,
-            "count": 33
+            "value": 1499946.0,
+            "min": 1019944.0,
+            "max": 1499946.0,
+            "count": 17
         },
         "Pyramids.Step.sum": {
-            "value": 989974.0,
-            "min": 29952.0,
-            "max": 989974.0,
-            "count": 33
+            "value": 1499946.0,
+            "min": 1019944.0,
+            "max": 1499946.0,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5462453961372375,
-            "min": -0.0893813818693161,
-            "max": 0.5539007186889648,
-            "count": 33
+            "value": 0.7240810990333557,
+            "min": 0.5280531644821167,
+            "max": 0.7240810990333557,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 151.85621643066406,
-            "min": -21.540912628173828,
-            "max": 152.32269287109375,
-            "count": 33
+            "value": 212.15576171875,
+            "min": 98.05105590820312,
+            "max": 212.15576171875,
+            "count": 17
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.030090928077697754,
-            "min": 0.0053176903165876865,
-            "max": 0.5040374398231506,
-            "count": 33
+            "value": -0.015062732622027397,
+            "min": -0.038299426436424255,
+            "max": 0.024049047380685806,
+            "count": 17
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 8.365278244018555,
-            "min": 1.3134695291519165,
-            "max": 119.45687866210938,
-            "count": 33
+            "value": -4.4133806228637695,
+            "min": -10.953636169433594,
+            "max": 6.661586284637451,
+            "count": 17
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7446271010627181,
+            "min": 1.5564873341856331,
+            "max": 1.7446271010627181,
+            "count": 17
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 205.86599792540073,
+            "min": 76.35099945962429,
+            "max": 205.86599792540073,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7446271010627181,
+            "min": 1.5564873341856331,
+            "max": 1.7446271010627181,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 205.86599792540073,
+            "min": 76.35099945962429,
+            "max": 205.86599792540073,
+            "count": 17
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.02108566748581124,
+            "min": 0.02108566748581124,
+            "max": 0.036422244585039495,
+            "count": 17
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.4881087633257266,
+            "min": 1.5972690338967368,
+            "max": 3.059468545143318,
+            "count": 17
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06962561037895891,
-            "min": 0.06543960634890308,
-            "max": 0.07392101677038451,
-            "count": 33
+            "value": 0.06781738295600716,
+            "min": 0.06358014467003245,
+            "max": 0.0706216018879786,
+            "count": 17
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9747585453054248,
-            "min": 0.4752439427639133,
-            "max": 1.0514126868391245,
-            "count": 33
+            "value": 0.9494433613841001,
+            "min": 0.6303121379799753,
+            "max": 1.0525073112221435,
+            "count": 17
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.014130477420708517,
-            "min": 0.0006469925694302089,
-            "max": 0.015236421878498047,
-            "count": 33
+            "value": 0.015996850570073582,
+            "min": 0.012975057341261871,
+            "max": 0.015996850570073582,
+            "count": 17
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.19782668388991925,
-            "min": 0.007763910833162507,
-            "max": 0.21330990629897265,
-            "count": 33
+            "value": 0.22395590798103016,
+            "min": 0.11677551607135683,
+            "max": 0.23405582210398276,
+            "count": 17
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.446461803592854e-06,
-            "min": 7.446461803592854e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 3.0954703967809542e-06,
+            "min": 3.0954703967809542e-06,
+            "max": 9.788917848140741e-05,
+            "count": 17
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010425046525029996,
-            "min": 0.00010425046525029996,
-            "max": 0.0035076809307730992,
-            "count": 33
+            "value": 4.333658555493336e-05,
+            "min": 4.333658555493336e-05,
+            "max": 0.0013029187656940667,
+            "count": 17
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10248212142857142,
-            "min": 0.10248212142857142,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10103179047619049,
+            "min": 0.10103179047619049,
+            "max": 0.13262970370370375,
+            "count": 17
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4347497,
-            "min": 1.3886848,
-            "max": 2.6176047000000002,
-            "count": 33
+            "value": 1.4144450666666668,
+            "min": 1.1936673333333336,
+            "max": 1.9053473333333335,
+            "count": 17
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025796393071428564,
-            "min": 0.00025796393071428564,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.00011307586857142865,
+            "min": 0.00011307586857142865,
+            "max": 0.0032697074000000003,
+            "count": 17
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036114950299999987,
-            "min": 0.0036114950299999987,
-            "max": 0.11694576731,
-            "count": 33
+            "value": 0.001583062160000001,
+            "min": 0.001583062160000001,
+            "max": 0.04352716274000001,
+            "count": 17
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.010309159755706787,
-            "min": 0.010206242091953754,
-            "max": 0.5324414372444153,
-            "count": 33
+            "value": 0.007952400483191013,
+            "min": 0.007952400483191013,
+            "max": 0.009898611344397068,
+            "count": 17
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.14432823657989502,
-            "min": 0.14288738369941711,
-            "max": 3.7270898818969727,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 346.775,
-            "min": 346.775,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 27742.0,
-            "min": 15984.0,
-            "max": 32633.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6282224778085947,
-            "min": -1.0000000521540642,
-            "max": 1.6282224778085947,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 130.25779822468758,
-            "min": -30.665001675486565,
-            "max": 142.41539785265923,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6282224778085947,
-            "min": -1.0000000521540642,
-            "max": 1.6282224778085947,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 130.25779822468758,
-            "min": -30.665001675486565,
-            "max": 142.41539785265923,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.03690245527232037,
-            "min": 0.03690245527232037,
-            "max": 11.691608242690563,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 2.9521964217856294,
-            "min": 2.9521964217856294,
-            "max": 187.065731883049,
-            "count": 33
+            "value": 0.11133360862731934,
+            "min": 0.08908750116825104,
+            "max": 0.13826604187488556,
+            "count": 17
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 17
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 17
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1717183678",
+        "start_time_seconds": "1717186256",
         "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": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1717185954"
+        "end_time_seconds": "1717187516"
     },
-    "total": 2275.489956409,
+    "total": 1259.4383329230004,
     "count": 1,
-    "self": 0.5888061000000562,
+    "self": 0.4760205799993855,
     "children": {
         "run_training.setup": {
-            "total": 0.08367152700020597,
+            "total": 0.05126818100052333,
             "count": 1,
-            "self": 0.08367152700020597
+            "self": 0.05126818100052333
         },
         "TrainerController.start_learning": {
-            "total": 2274.817478782,
+            "total": 1258.9110441620005,
             "count": 1,
-            "self": 1.538024738981676,
+            "self": 0.7677809090109804,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.7331542339998123,
+                    "total": 2.232809957000427,
                     "count": 1,
-                    "self": 2.7331542339998123
+                    "self": 2.232809957000427
                 },
                 "TrainerController.advance": {
-                    "total": 2270.450689360018,
-                    "count": 63913,
-                    "self": 1.5674759250487114,
+                    "total": 1255.822123611989,
+                    "count": 32541,
+                    "self": 0.8053479979917029,
                     "children": {
                         "env_step": {
-                            "total": 1620.7483550599673,
-                            "count": 63913,
-                            "self": 1481.048849954071,
+                            "total": 931.4630197449387,
+                            "count": 32541,
+                            "self": 860.8604555749016,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 138.7712550989204,
-                                    "count": 63913,
-                                    "self": 4.944066397851657,
+                                    "total": 70.13547415700396,
+                                    "count": 32541,
+                                    "self": 2.5215686200272103,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 133.82718870106874,
-                                            "count": 62548,
-                                            "self": 133.82718870106874
+                                            "total": 67.61390553697674,
+                                            "count": 31295,
+                                            "self": 67.61390553697674
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9282500069757589,
-                                    "count": 63913,
+                                    "total": 0.46709001303315745,
+                                    "count": 32541,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2269.5709389880076,
-                                            "count": 63913,
+                                            "total": 1256.027467099957,
+                                            "count": 32541,
                                             "is_parallel": true,
-                                            "self": 920.9424124769994,
+                                            "self": 461.83187196688505,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002737472999797319,
+                                                            "total": 0.0021142400000826456,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00073389799990764,
+                                                            "self": 0.0006239159993128851,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002003574999889679,
+                                                                    "total": 0.0014903240007697605,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002003574999889679
+                                                                    "self": 0.0014903240007697605
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04954141400003209,
+                                                            "total": 0.088227979000294,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006079439999666647,
+                                                            "self": 0.0006633509992752806,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004395400001158123,
+                                                                    "total": 0.0005221680003160145,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004395400001158123
+                                                                    "self": 0.0005221680003160145
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04684194399987973,
+                                                                    "total": 0.08452152000063506,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04684194399987973
+                                                                    "self": 0.08452152000063506
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016519860000698827,
+                                                                    "total": 0.0025209400000676396,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003357330010658188,
+                                                                    "self": 0.0004011549999631825,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001316252999004064,
+                                                                            "total": 0.002119785000104457,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001316252999004064
+                                                                            "self": 0.002119785000104457
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1348.6285265110082,
-                                                    "count": 63912,
+                                                    "total": 794.195595133072,
+                                                    "count": 32540,
                                                     "is_parallel": true,
-                                                    "self": 34.89706483396503,
+                                                    "self": 17.651247055092426,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 24.33059817400681,
-                                                            "count": 63912,
+                                                            "total": 12.197150454011535,
+                                                            "count": 32540,
                                                             "is_parallel": true,
-                                                            "self": 24.33059817400681
+                                                            "self": 12.197150454011535
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1185.3089984420017,
-                                                            "count": 63912,
+                                                            "total": 711.9384423460306,
+                                                            "count": 32540,
                                                             "is_parallel": true,
-                                                            "self": 1185.3089984420017
+                                                            "self": 711.9384423460306
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 104.0918650610347,
-                                                            "count": 63912,
+                                                            "total": 52.408755277937416,
+                                                            "count": 32540,
                                                             "is_parallel": true,
-                                                            "self": 21.837636461088096,
+                                                            "self": 10.992631100058134,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 82.2542285999466,
-                                                                    "count": 511296,
+                                                                    "total": 41.41612417787928,
+                                                                    "count": 260320,
                                                                     "is_parallel": true,
-                                                                    "self": 82.2542285999466
+                                                                    "self": 41.41612417787928
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 648.1348583750018,
-                            "count": 63913,
-                            "self": 2.8002164059676034,
+                            "total": 323.5537558690585,
+                            "count": 32541,
+                            "self": 1.5293286400828947,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 134.42033066303338,
-                                    "count": 63913,
-                                    "self": 134.16502085903312,
+                                    "total": 69.16295337697557,
+                                    "count": 32541,
+                                    "self": 69.05397919097504,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2553098040002624,
-                                            "count": 2,
-                                            "self": 0.2553098040002624
+                                            "total": 0.10897418600052333,
+                                            "count": 1,
+                                            "self": 0.10897418600052333
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 510.91431130600085,
-                                    "count": 451,
-                                    "self": 304.887499234972,
+                                    "total": 252.86147385200002,
+                                    "count": 236,
+                                    "self": 149.54518986398216,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 206.02681207102887,
-                                            "count": 22785,
-                                            "self": 206.02681207102887
+                                            "total": 103.31628398801786,
+                                            "count": 11364,
+                                            "self": 103.31628398801786
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.4060005923965946e-06,
+                    "total": 1.002999852062203e-06,
                     "count": 1,
-                    "self": 1.4060005923965946e-06
+                    "self": 1.002999852062203e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09560904299996764,
+                    "total": 0.0883286810003483,
                     "count": 1,
-                    "self": 0.0014479080000455724,
+                    "self": 0.0020003220006401534,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09416113499992207,
+                            "total": 0.08632835899970814,
                             "count": 1,
-                            "self": 0.09416113499992207
+                            "self": 0.08632835899970814
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499956,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499956.onnx",
-                "reward": 1.477999985218048,
-                "creation_time": 1717184748.4960434,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499956.pt"
-                ]
-            },
             {
                 "steps": 999897,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-999897.onnx",
@@ -27,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000025.pt"
                 ]
+            },
+            {
+                "steps": 1000025,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000025.onnx",
+                "reward": null,
+                "creation_time": 1717186223.6156945,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000025.pt"
+                ]
+            },
+            {
+                "steps": 1499946,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499946.onnx",
+                "reward": 1.7529999703168868,
+                "creation_time": 1717187515.7098098,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499946.pt"
+                ]
+            },
+            {
+                "steps": 1500074,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1500074.onnx",
+                "reward": 1.7529999703168868,
+                "creation_time": 1717187515.8058512,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1500074.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000025,
+            "steps": 1500074,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1717185953.7424698,
+            "reward": 1.7529999703168868,
+            "creation_time": 1717187515.8058512,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000025.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1500074.pt"
             ]
         }
     },