Second Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c09b00193de46d7f365fd758579ba6a0485c0efd5db06917cf917fbcc35043
+oid sha256:5a39876487d339c4b208e6411579055a06164a9f9465d564bbd543d8c11b0567
 size 1420238

Pyramids/Pyramids-1499991.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16e03dc259ff7c4779cb1a9502daccf7d80132001c99574125ffc04d67fa9a7
+size 1420238

Pyramids/Pyramids-1499991.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1a7613d8e3f673c9d866acdc9dfa97f131ebe596fe95379d4f54ddede4f6ac
+size 8656731

Pyramids/Pyramids-1800095.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a39876487d339c4b208e6411579055a06164a9f9465d564bbd543d8c11b0567
+size 1420238

Pyramids/Pyramids-1800095.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f29a56514f4ece4a996490ae27deaceae584256bd83ccd0ff9ddb05dea804046
+size 8656731

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e423689916d8306c89937d148f9ad4bc2767ada9bf62a5dc086a12be08649a7
+oid sha256:896be9ddc11c73f37b80a1531b9620fd31dff6c229ed78259c49f21d3d4e049f
 size 8656181

Pyramids/events.out.tfevents.1762951088.245817e23d78.38814.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77237f3d2d8edc5941a01fa233cef93a8d64f2848cb77eb9dbcb6e874b3a38b7
+size 152599

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": 1200000, "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": 1800000, "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: 1200000
+    max_steps: 1800000
     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] 55037 [Flags] 2 [Guid] 940311219 [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] 55292 [Flags] 2 [Guid] 1201022217 [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  0.135 seconds
+- Completed reload, in  0.091 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: 1.085109 ms
+UnloadTime: 0.807321 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.
@@ -81,7 +78,7 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4592 frames, [32.0 KB-64.0 KB]: 12838 frames, [64.0 KB-128.0 KB]: 5090 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1298 frames, [32.0 KB-64.0 KB]: 6113 frames, [64.0 KB-128.0 KB]: 3856 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
@@ -126,7 +123,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -136,7 +133,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       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]: 22222 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 33 frames, [1.0 MB-2.0 MB]: 11235 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 12856
+  Peak main deferred allocation count 13094
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 22520 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 11267 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 31.6 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]: 22521 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 11268 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.1 MB
+      Peak Allocated memory 22.0 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 1.3 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 22520 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 11267 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]: 22521 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 11268 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,39 +270,39 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 22222 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 37 frames, [1.0 MB-2.0 MB]: 11231 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]: 22520 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 11267 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.2 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 1.3 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 22521 frames
+      Peak usage frame count: [0-1.0 KB]: 11268 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]: 22521 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 11268 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]: 22521 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 11268 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1762948266065,"processId":15438,"allocatedMemory":1970545,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":11015},{"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":1762952568480,"processId":38840,"allocatedMemory":1970545,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":11015},{"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": 0.3065645694732666,
-            "min": 0.3065645694732666,
-            "max": 1.5370512008666992,
-            "count": 40
+            "value": 0.18347740173339844,
+            "min": 0.16536884009838104,
+            "max": 0.3051706850528717,
+            "count": 20
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 9250.892578125,
-            "min": 9250.892578125,
-            "max": 46627.984375,
-            "count": 40
+            "value": 5539.5498046875,
+            "min": 4908.14697265625,
+            "max": 9409.0224609375,
+            "count": 20
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 257.2357723577236,
+            "min": 229.29032258064515,
+            "max": 286.1926605504587,
+            "count": 20
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 31640.0,
+            "min": 28432.0,
+            "max": 31640.0,
+            "count": 20
         },
         "Pyramids.Step.mean": {
-            "value": 1199915.0,
-            "min": 29952.0,
-            "max": 1199915.0,
-            "count": 40
+            "value": 1799967.0,
+            "min": 1229987.0,
+            "max": 1799967.0,
+            "count": 20
         },
         "Pyramids.Step.sum": {
-            "value": 1199915.0,
-            "min": 29952.0,
-            "max": 1199915.0,
-            "count": 40
+            "value": 1799967.0,
+            "min": 1229987.0,
+            "max": 1799967.0,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7182618975639343,
-            "min": -0.09630430489778519,
-            "max": 0.737196683883667,
-            "count": 40
+            "value": 0.7283996939659119,
+            "min": 0.6516091227531433,
+            "max": 0.7944933772087097,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 210.4507293701172,
-            "min": -22.827098846435547,
-            "max": 216.5155792236328,
-            "count": 40
+            "value": 212.6927032470703,
+            "min": 187.01181030273438,
+            "max": 236.759033203125,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.026296285912394524,
-            "min": -0.0008869227021932602,
-            "max": 0.1875319480895996,
-            "count": 40
+            "value": -0.01562570407986641,
+            "min": -0.01562570407986641,
+            "max": 0.047894831746816635,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 7.7048115730285645,
-            "min": -0.24035605788230896,
-            "max": 45.007667541503906,
-            "count": 40
+            "value": -4.5627055168151855,
+            "min": -4.5627055168151855,
+            "max": 13.841606140136719,
+            "count": 20
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6614390073752985,
+            "min": 1.6528878328956176,
+            "max": 1.7657983686414458,
+            "count": 20
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 204.3569979071617,
+            "min": 175.7153990715742,
+            "max": 221.81499876081944,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6614390073752985,
+            "min": 1.6528878328956176,
+            "max": 1.7657983686414458,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 204.3569979071617,
+            "min": 175.7153990715742,
+            "max": 221.81499876081944,
+            "count": 20
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.021665721189995425,
+            "min": 0.020442040216332603,
+            "max": 0.026402303401928808,
+            "count": 20
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.6648837063694373,
+            "min": 2.473486866176245,
+            "max": 2.960366822386277,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07093865501589053,
-            "min": 0.06506594679307282,
-            "max": 0.07336528825150741,
-            "count": 40
+            "value": 0.0696433908888139,
+            "min": 0.06593222917426549,
+            "max": 0.07108483445370525,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9931411702224674,
-            "min": 0.49500045787620667,
-            "max": 1.091939311241731,
-            "count": 40
+            "value": 0.9750074724433945,
+            "min": 0.9230512084397169,
+            "max": 1.056874103579378,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.014747422073491005,
-            "min": 0.000887932243720887,
-            "max": 0.01726262353746597,
-            "count": 40
+            "value": 0.015932606914984285,
+            "min": 0.012798120494283336,
+            "max": 0.016656490289617566,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.20646390902887407,
-            "min": 0.011175363583208371,
-            "max": 0.23745870499503025,
-            "count": 40
+            "value": 0.22305649680977999,
+            "min": 0.1791736869199667,
+            "max": 0.23319086405464592,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 3.772884456690476e-06,
-            "min": 3.772884456690476e-06,
-            "max": 0.0002959588584899048,
-            "count": 40
+            "value": 2.4778848883571454e-06,
+            "min": 2.4778848883571454e-06,
+            "max": 9.736857944859126e-05,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 5.2820382393666664e-05,
-            "min": 5.2820382393666664e-05,
-            "max": 0.0037278944073685827,
-            "count": 40
+            "value": 3.4690388437000035e-05,
+            "min": 3.4690388437000035e-05,
+            "max": 0.0013631601122802777,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10125759523809526,
-            "min": 0.10125759523809526,
-            "max": 0.1986529523809524,
-            "count": 40
+            "value": 0.10082592857142857,
+            "min": 0.10082592857142857,
+            "max": 0.13245617063492066,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4176063333333335,
-            "min": 1.3742613333333336,
-            "max": 2.7185890833333333,
-            "count": 40
+            "value": 1.411563,
+            "min": 1.411563,
+            "max": 1.8625565555555554,
+            "count": 20
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0001356337642857143,
-            "min": 0.0001356337642857143,
-            "max": 0.00986542994285714,
-            "count": 40
+            "value": 9.251026428571435e-05,
+            "min": 9.251026428571435e-05,
+            "max": 0.003252371446428571,
+            "count": 20
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0018988727000000003,
-            "min": 0.0018988727000000003,
-            "max": 0.12427887852499998,
-            "count": 40
+            "value": 0.0012951437000000008,
+            "min": 0.0012951437000000008,
+            "max": 0.045533200249999996,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.008802435360848904,
-            "min": 0.008686560206115246,
-            "max": 0.3637855052947998,
-            "count": 40
+            "value": 0.008193425834178925,
+            "min": 0.008193425834178925,
+            "max": 0.009500919841229916,
+            "count": 20
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.1232341006398201,
-            "min": 0.1232341006398201,
-            "max": 2.5464985370635986,
-            "count": 40
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 262.462962962963,
-            "min": 245.28099173553719,
-            "max": 999.0,
-            "count": 40
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28346.0,
-            "min": 15984.0,
-            "max": 32634.0,
-            "count": 40
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7196366785589707,
-            "min": -1.0000000521540642,
-            "max": 1.7425887683563144,
-            "count": 40
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 187.44039796292782,
-            "min": -32.000001668930054,
-            "max": 210.32019817829132,
-            "count": 40
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7196366785589707,
-            "min": -1.0000000521540642,
-            "max": 1.7425887683563144,
-            "count": 40
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 187.44039796292782,
-            "min": -32.000001668930054,
-            "max": 210.32019817829132,
-            "count": 40
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.024062973982027044,
-            "min": 0.02362177784457304,
-            "max": 7.509727615863085,
-            "count": 40
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 2.622864164040948,
-            "min": 2.622864164040948,
-            "max": 120.15564185380936,
-            "count": 40
+            "value": 0.11470796167850494,
+            "min": 0.11470796167850494,
+            "max": 0.13423441350460052,
+            "count": 20
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 20
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1762945555",
+        "start_time_seconds": "1762951087",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "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 --resume --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1762948266"
+        "end_time_seconds": "1762952568"
     },
-    "total": 2710.7790318679995,
+    "total": 1480.701929109,
     "count": 1,
-    "self": 0.48100764399987384,
+    "self": 0.532957625000563,
     "children": {
         "run_training.setup": {
-            "total": 0.03607006599986562,
+            "total": 0.023814800999389263,
             "count": 1,
-            "self": 0.03607006599986562
+            "self": 0.023814800999389263
         },
         "TrainerController.start_learning": {
-            "total": 2710.2619541579998,
+            "total": 1480.145156683,
             "count": 1,
-            "self": 1.5980979019836923,
+            "self": 0.7973223673343455,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.3161829149998994,
+                    "total": 2.084303745001307,
                     "count": 1,
-                    "self": 2.3161829149998994
+                    "self": 2.084303745001307
                 },
                 "TrainerController.advance": {
-                    "total": 2706.262438678017,
-                    "count": 77363,
-                    "self": 1.6221687942120298,
+                    "total": 1477.1874179816623,
+                    "count": 39419,
+                    "self": 0.8337124696463434,
                     "children": {
                         "env_step": {
-                            "total": 1925.2577880499207,
-                            "count": 77363,
-                            "self": 1751.263634797932,
+                            "total": 1089.8707667620656,
+                            "count": 39419,
+                            "self": 1002.9535249321434,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 173.09866128397698,
-                                    "count": 77363,
-                                    "self": 5.354987104010888,
+                                    "total": 86.43570298192208,
+                                    "count": 39419,
+                                    "self": 2.7428888748327154,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 167.7436741799661,
-                                            "count": 75069,
-                                            "self": 167.7436741799661
+                                            "total": 83.69281410708936,
+                                            "count": 37559,
+                                            "self": 83.69281410708936
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.895491968011811,
-                                    "count": 77363,
+                                    "total": 0.4815388480001275,
+                                    "count": 39419,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2702.9702042778945,
-                                            "count": 77363,
+                                            "total": 1476.2343495521945,
+                                            "count": 39419,
                                             "is_parallel": true,
-                                            "self": 1087.4012424187154,
+                                            "self": 542.2397924860525,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0019287269997221301,
+                                                            "total": 0.001774239999576821,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006215499993231788,
+                                                            "self": 0.000596388999838382,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013071770003989513,
+                                                                    "total": 0.001177850999738439,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013071770003989513
+                                                                    "self": 0.001177850999738439
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.047738590000335535,
+                                                            "total": 0.05186884599970654,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005209089999880234,
+                                                            "self": 0.0005691830010619015,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004781460002050153,
+                                                                    "total": 0.0004935919987474335,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004781460002050153
+                                                                    "self": 0.0004935919987474335
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04509997500008467,
+                                                                    "total": 0.04909174000022176,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04509997500008467
+                                                                    "self": 0.04909174000022176
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001639560000057827,
+                                                                    "total": 0.0017143309996754397,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00033114899997599423,
+                                                                    "self": 0.00032570099938311614,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013084110000818328,
+                                                                            "total": 0.0013886300002923235,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013084110000818328
+                                                                            "self": 0.0013886300002923235
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1615.5689618591791,
-                                                    "count": 77362,
+                                                    "total": 933.9945570661421,
+                                                    "count": 39418,
                                                     "is_parallel": true,
-                                                    "self": 39.94426892824413,
+                                                    "self": 19.88177738012928,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 27.67737105297556,
-                                                            "count": 77362,
+                                                            "total": 13.84117243197943,
+                                                            "count": 39418,
                                                             "is_parallel": true,
-                                                            "self": 27.67737105297556
+                                                            "self": 13.84117243197943
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1419.4534093040238,
-                                                            "count": 77362,
+                                                            "total": 835.4911941160371,
+                                                            "count": 39418,
                                                             "is_parallel": true,
-                                                            "self": 1419.4534093040238
+                                                            "self": 835.4911941160371
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 128.49391257393563,
-                                                            "count": 77362,
+                                                            "total": 64.78041313799622,
+                                                            "count": 39418,
                                                             "is_parallel": true,
-                                                            "self": 26.633117993859287,
+                                                            "self": 13.512100370020562,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 101.86079458007634,
-                                                                    "count": 618896,
+                                                                    "total": 51.26831276797566,
+                                                                    "count": 315344,
                                                                     "is_parallel": true,
-                                                                    "self": 101.86079458007634
+                                                                    "self": 51.26831276797566
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 779.3824818338844,
-                            "count": 77363,
-                            "self": 3.0478392476884437,
+                            "total": 386.48293874995034,
+                            "count": 39419,
+                            "self": 1.6931462749180355,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 150.5790787801866,
-                                    "count": 77363,
-                                    "self": 150.2969701061861,
+                                    "total": 77.74215061902578,
+                                    "count": 39419,
+                                    "self": 77.63888940402649,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.282108674000483,
-                                            "count": 2,
-                                            "self": 0.282108674000483
+                                            "total": 0.10326121499929286,
+                                            "count": 1,
+                                            "self": 0.10326121499929286
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 625.7555638060094,
-                                    "count": 548,
-                                    "self": 348.8780211410017,
+                                    "total": 307.0476418560065,
+                                    "count": 283,
+                                    "self": 171.16670905297906,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 276.8775426650077,
-                                            "count": 27354,
-                                            "self": 276.8775426650077
+                                            "total": 135.88093280302746,
+                                            "count": 13647,
+                                            "self": 135.88093280302746
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0409994501969777e-06,
+                    "total": 8.880015229806304e-07,
                     "count": 1,
-                    "self": 1.0409994501969777e-06
+                    "self": 8.880015229806304e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08523362199957774,
+                    "total": 0.07611170100062736,
                     "count": 1,
-                    "self": 0.001038592999066168,
+                    "self": 0.0013987319998705061,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08419502900051157,
+                            "total": 0.07471296900075686,
                             "count": 1,
-                            "self": 0.08419502900051157
+                            "self": 0.07471296900075686
                         }
                     }
                 }

run_logs/training_status.json

@@ -27,15 +27,33 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1200043.pt"
                 ]
+            },
+            {
+                "steps": 1499991,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499991.onnx",
+                "reward": 1.80159994661808,
+                "creation_time": 1762951833.1666663,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499991.pt"
+                ]
+            },
+            {
+                "steps": 1800095,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1800095.onnx",
+                "reward": 1.8269999836172377,
+                "creation_time": 1762952568.011504,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1800095.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1200043,
+            "steps": 1800095,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7118571400642395,
-            "creation_time": 1762948265.636365,
+            "reward": 1.8269999836172377,
+            "creation_time": 1762952568.011504,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1200043.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1800095.pt"
             ]
         }
     },