Second Pyramids

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7138c100763aaea7ebd31ac14942e1771b8968d484a19f449b72d4e79348987
+oid sha256:440e9383a11a9d2fcd2b0ab3f034164692ae42972551d5c2005eaf9034f8988e
 size 1417437

Pyramids/Pyramids-1000041.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440e9383a11a9d2fcd2b0ab3f034164692ae42972551d5c2005eaf9034f8988e
+size 1417437

Pyramids/Pyramids-1000041.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2342ba179920f33137624ee17dab57a5ce8e5aa52b747b3b279525f477d0540
+size 8652382

Pyramids/Pyramids-500071.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37b586a6f72cbc60cf05a19d364b823b0169242be3d47970ab21255f99abb2b
+oid sha256:216a2f6f59c6ae348a454e720c69a0ef827b3a5d51d35e62c3f3353788022d91
 size 8652382

Pyramids/Pyramids-999913.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440e9383a11a9d2fcd2b0ab3f034164692ae42972551d5c2005eaf9034f8988e
+size 1417437

Pyramids/Pyramids-999913.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56baed909aded2f599447dba491ac2bcca36bb09b81647d05705d0435af5a151
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37b586a6f72cbc60cf05a19d364b823b0169242be3d47970ab21255f99abb2b
+oid sha256:e2342ba179920f33137624ee17dab57a5ce8e5aa52b747b3b279525f477d0540
 size 8652382

Pyramids/events.out.tfevents.1666820377.130dbf9bc22c.814.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41f1e8e9b4dbc7a6f1dac77e9cf5df2f7faeebba1103b2c60bb650ec871f7f0
+size 1325

Pyramids/events.out.tfevents.1666820414.130dbf9bc22c.883.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092ecaa83c5256f4a68e98b4c8929dd0c94aa5e241a91cf444beadd71666b54d
+size 167892

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "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

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 500000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -78,7 +78,7 @@ 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/trained-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55091 [Flags] 2 [Guid] 1591412839 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55045 [Flags] 2 [Guid] 2755707121 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [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/trained-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2495:(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  0.087 seconds
+- Completed reload, in  0.083 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -68,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.960260 ms
+UnloadTime: 0.829729 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]: 3793 frames, [32.0 KB-64.0 KB]: 4890 frames, [64.0 KB-128.0 KB]: 705 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1911 frames, [32.0 KB-64.0 KB]: 5871 frames, [64.0 KB-128.0 KB]: 1613 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
@@ -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]: 9090 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 125 frames, [1.0 MB-2.0 MB]: 9271 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.3 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12850
+  Peak main deferred allocation count 10274
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 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]: 9388 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9395 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 31.7 MB
+      Peak Block count 2
+      Peak Allocated memory 24.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9389 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9396 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.5 MB
+      Peak Allocated memory 22.5 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 1.5 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9388 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9395 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]: 9389 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 9396 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 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]: 9090 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 154 frames, [1.0 MB-2.0 MB]: 9242 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]: 9388 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 9395 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -291,21 +288,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9389 frames
+      Peak usage frame count: [0-1.0 KB]: 9396 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]: 9389 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9396 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]: 9389 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 9396 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":1666819880934,"processId":248,"allocatedMemory":1957329,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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":3444},{"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":1666821515887,"processId":894,"allocatedMemory":1957329,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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":3444},{"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

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.9084978699684143,
-            "min": 0.8695369958877563,
-            "max": 1.3743906021118164,
-            "count": 16
+            "value": 0.5548450350761414,
+            "min": 0.5548450350761414,
+            "max": 0.9097636938095093,
+            "count": 17
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 27211.328125,
-            "min": 26294.798828125,
-            "max": 41693.51171875,
-            "count": 16
+            "value": 16538.8203125,
+            "min": 9048.5341796875,
+            "max": 27394.8046875,
+            "count": 17
         },
         "Pyramids.Step.mean": {
-            "value": 479940.0,
-            "min": 29909.0,
-            "max": 479940.0,
-            "count": 16
+            "value": 989877.0,
+            "min": 509969.0,
+            "max": 989877.0,
+            "count": 17
         },
         "Pyramids.Step.sum": {
-            "value": 479940.0,
-            "min": 29909.0,
-            "max": 479940.0,
-            "count": 16
+            "value": 989877.0,
+            "min": 509969.0,
+            "max": 989877.0,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.018997682258486748,
-            "min": -0.11020457744598389,
-            "max": 0.018997682258486748,
-            "count": 16
+            "value": 0.4498426616191864,
+            "min": 0.018395353108644485,
+            "max": 0.47865211963653564,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 4.65443229675293,
-            "min": -26.559303283691406,
-            "max": 4.65443229675293,
-            "count": 16
+            "value": 121.00767517089844,
+            "min": 1.471628189086914,
+            "max": 130.67202758789062,
+            "count": 17
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.022452151402831078,
-            "min": 0.007125687785446644,
-            "max": 0.5450734496116638,
-            "count": 16
+            "value": -0.15813587605953217,
+            "min": -0.15813587605953217,
+            "max": 0.18717536330223083,
+            "count": 17
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 5.500777244567871,
-            "min": 1.7315421104431152,
-            "max": 129.18240356445312,
-            "count": 16
+            "value": -42.538551330566406,
+            "min": -42.538551330566406,
+            "max": 50.537349700927734,
+            "count": 17
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06771395367088255,
-            "min": 0.06413732348084195,
-            "max": 0.07473053815184147,
-            "count": 16
+            "value": 0.06940189483256767,
+            "min": 0.06384416604364038,
+            "max": 0.07085341716899786,
+            "count": 17
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9479953513923558,
-            "min": 0.5071190284692546,
-            "max": 1.0193372554706144,
-            "count": 16
+            "value": 0.9716265276559474,
+            "min": 0.21131838193590136,
+            "max": 1.0338376412298256,
+            "count": 17
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0061463462096986035,
-            "min": 0.0007270691751884686,
-            "max": 0.012247806203890347,
-            "count": 16
+            "value": 0.02051455678502818,
+            "min": 0.004671117367647003,
+            "max": 0.02051455678502818,
+            "count": 17
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.08604884693578045,
-            "min": 0.01017896845263856,
-            "max": 0.08604884693578045,
-            "count": 16
+            "value": 0.28720379499039456,
+            "min": 0.021576496421403135,
+            "max": 0.28720379499039456,
+            "count": 17
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.0732278803557146e-05,
-            "min": 2.0732278803557146e-05,
-            "max": 0.00029046951746254277,
-            "count": 16
+            "value": 7.646754593971431e-06,
+            "min": 7.646754593971431e-06,
+            "max": 0.0001481200506266667,
+            "count": 17
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00029025190324980004,
-            "min": 0.00029025190324980004,
-            "max": 0.0028541775486075997,
-            "count": 16
+            "value": 0.00010705456431560002,
+            "min": 0.00010705456431560002,
+            "max": 0.0019958326347227,
+            "count": 17
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10691072857142857,
-            "min": 0.10691072857142857,
-            "max": 0.19682317142857148,
-            "count": 16
+            "value": 0.10254888571428573,
+            "min": 0.10254888571428573,
+            "max": 0.14937333333333333,
+            "count": 17
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4967502,
-            "min": 1.3777622000000003,
-            "max": 2.3387318,
-            "count": 16
+            "value": 1.4356844000000002,
+            "min": 0.44811999999999996,
+            "max": 2.0773133,
+            "count": 17
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0007003817842857143,
-            "min": 0.0007003817842857143,
-            "max": 0.009682634825714284,
-            "count": 16
+            "value": 0.0002646336828571429,
+            "min": 0.0002646336828571429,
+            "max": 0.004942395999999999,
+            "count": 17
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.00980534498,
-            "min": 0.00980534498,
-            "max": 0.09517410075999999,
-            "count": 16
+            "value": 0.003704871560000001,
+            "min": 0.003704871560000001,
+            "max": 0.06660120227,
+            "count": 17
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.020159462466835976,
-            "min": 0.020159462466835976,
-            "max": 0.613907516002655,
-            "count": 16
+            "value": 0.011130442842841148,
+            "min": 0.011130442842841148,
+            "max": 0.018592344596982002,
+            "count": 17
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.28223246335983276,
-            "min": 0.28223246335983276,
-            "max": 4.2973527908325195,
-            "count": 16
+            "value": 0.15582619607448578,
+            "min": 0.055777035653591156,
+            "max": 0.25444158911705017,
+            "count": 17
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 856.4,
-            "min": 856.4,
-            "max": 999.0,
-            "count": 16
+            "value": 381.958904109589,
+            "min": 381.958904109589,
+            "max": 835.3428571428572,
+            "count": 17
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29974.0,
-            "min": 16708.0,
-            "max": 33122.0,
-            "count": 16
+            "value": 27883.0,
+            "min": 2341.0,
+            "max": 31805.0,
+            "count": 17
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.0003542389188494001,
-            "min": -0.9999500517733395,
-            "max": 0.0003542389188494001,
-            "count": 16
+            "value": 1.5632301107661364,
+            "min": -0.04676927492404596,
+            "max": 1.5632301107661364,
+            "count": 17
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 0.012398362159729004,
-            "min": -31.998401656746864,
-            "max": 0.012398362159729004,
-            "count": 16
+            "value": 114.11579808592796,
+            "min": -1.8240017220377922,
+            "max": 114.88739801198244,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.0003542389188494001,
-            "min": -0.9999500517733395,
-            "max": 0.0003542389188494001,
-            "count": 16
+            "value": 1.5632301107661364,
+            "min": -0.04676927492404596,
+            "max": 1.5632301107661364,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 0.012398362159729004,
-            "min": -31.998401656746864,
-            "max": 0.012398362159729004,
-            "count": 16
+            "value": 114.11579808592796,
+            "min": -1.8240017220377922,
+            "max": 114.88739801198244,
+            "count": 17
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.1820826190124665,
-            "min": 0.1820826190124665,
-            "max": 12.796114008216296,
-            "count": 16
+            "value": 0.04380278093405451,
+            "min": 0.04380278093405451,
+            "max": 0.15401908088750085,
+            "count": 17
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 6.3728916654363275,
-            "min": 6.3728916654363275,
-            "max": 217.53393813967705,
-            "count": 16
+            "value": 3.197603008185979,
+            "min": 0.4970928718103096,
+            "max": 6.006744154612534,
+            "count": 17
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 17
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 17
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1666818869",
+        "start_time_seconds": "1666820411",
         "python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1666819880"
+        "end_time_seconds": "1666821515"
     },
-    "total": 1011.783349114,
+    "total": 1104.50703153,
     "count": 1,
-    "self": 0.5902997279998772,
+    "self": 0.44053384599965284,
     "children": {
         "run_training.setup": {
-            "total": 0.050986602000079984,
+            "total": 0.043343765000372514,
             "count": 1,
-            "self": 0.050986602000079984
+            "self": 0.043343765000372514
         },
         "TrainerController.start_learning": {
-            "total": 1011.142062784,
+            "total": 1104.023153919,
             "count": 1,
-            "self": 0.7855666959927703,
+            "self": 0.8265517110116889,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 8.35925892399996,
+                    "total": 6.503371287999926,
                     "count": 1,
-                    "self": 8.35925892399996
+                    "self": 6.503371287999926
                 },
                 "TrainerController.advance": {
-                    "total": 1001.8960520210072,
-                    "count": 31596,
-                    "self": 0.8521182120000503,
+                    "total": 1096.5990557029882,
+                    "count": 32026,
+                    "self": 0.8887431339071554,
                     "children": {
                         "env_step": {
-                            "total": 642.8877986339994,
-                            "count": 31596,
-                            "self": 586.1532477040063,
+                            "total": 734.722037918054,
+                            "count": 32026,
+                            "self": 676.3580663430766,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 56.326923302005525,
-                                    "count": 31596,
-                                    "self": 2.3870449230020085,
+                                    "total": 57.92033342601144,
+                                    "count": 32026,
+                                    "self": 2.486959676054994,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 53.93987837900352,
-                                            "count": 31295,
-                                            "self": 18.123204745994485,
+                                            "total": 55.433373749956445,
+                                            "count": 31318,
+                                            "self": 18.669532147922382,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 35.81667363300903,
-                                                    "count": 31295,
-                                                    "self": 35.81667363300903
+                                                    "total": 36.76384160203406,
+                                                    "count": 31318,
+                                                    "self": 36.76384160203406
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.4076276279876083,
-                                    "count": 31596,
+                                    "total": 0.4436381489658743,
+                                    "count": 32026,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1008.6657898970321,
-                                            "count": 31596,
+                                            "total": 1101.6087957520535,
+                                            "count": 32026,
                                             "is_parallel": true,
-                                            "self": 476.14142705004167,
+                                            "self": 481.4929296781247,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0054870179999397806,
+                                                            "total": 0.0019209470001442241,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004294937999929971,
+                                                            "self": 0.0007091149991538259,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0011920800000098097,
+                                                                    "total": 0.0012118320009903982,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0011920800000098097
+                                                                    "self": 0.0012118320009903982
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04871491699998387,
+                                                            "total": 0.060161157000038656,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005131700000902129,
+                                                            "self": 0.0005135700002938393,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004532350000090446,
+                                                                    "total": 0.0004762000003211142,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004532350000090446
+                                                                    "self": 0.0004762000003211142
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.046149886999955925,
+                                                                    "total": 0.05752015199959715,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.046149886999955925
+                                                                    "self": 0.05752015199959715
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0015986249999286883,
+                                                                    "total": 0.0016512349998265563,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00045194599999831553,
+                                                                    "self": 0.000425104999976611,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0011466789999303728,
+                                                                            "total": 0.0012261299998499453,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0011466789999303728
+                                                                            "self": 0.0012261299998499453
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 532.5243628469905,
-                                                    "count": 31595,
+                                                    "total": 620.1158660739288,
+                                                    "count": 32025,
                                                     "is_parallel": true,
-                                                    "self": 14.533061375969282,
+                                                    "self": 14.729850475844614,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 12.09291369999687,
-                                                            "count": 31595,
+                                                            "total": 12.183287286025916,
+                                                            "count": 32025,
                                                             "is_parallel": true,
-                                                            "self": 12.09291369999687
+                                                            "self": 12.183287286025916
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 453.8168250310167,
-                                                            "count": 31595,
+                                                            "total": 545.050911685014,
+                                                            "count": 32025,
                                                             "is_parallel": true,
-                                                            "self": 453.8168250310167
+                                                            "self": 545.050911685014
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 52.0815627400076,
-                                                            "count": 31595,
+                                                            "total": 48.151816627044354,
+                                                            "count": 32025,
                                                             "is_parallel": true,
-                                                            "self": 12.297747187055393,
+                                                            "self": 12.507719423942035,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 39.783815552952206,
-                                                                    "count": 252760,
+                                                                    "total": 35.64409720310232,
+                                                                    "count": 256200,
                                                                     "is_parallel": true,
-                                                                    "self": 39.783815552952206
+                                                                    "self": 35.64409720310232
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 358.15613517500776,
-                            "count": 31596,
-                            "self": 1.3401801439998735,
+                            "total": 360.98827465102704,
+                            "count": 32026,
+                            "self": 1.5785568430037529,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 80.92426566900792,
-                                    "count": 31596,
-                                    "self": 80.816182289008,
+                                    "total": 82.8166930020293,
+                                    "count": 32026,
+                                    "self": 82.70609321602933,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.10808337999992546,
+                                            "total": 0.11059978599996612,
                                             "count": 1,
-                                            "self": 0.10808337999992546
+                                            "self": 0.11059978599996612
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 275.89168936199997,
-                                    "count": 216,
-                                    "self": 108.7441741229984,
+                                    "total": 276.593024805994,
+                                    "count": 234,
+                                    "self": 109.23629919799805,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 167.14751523900156,
-                                            "count": 11421,
-                                            "self": 167.14751523900156
+                                            "total": 167.35672560799594,
+                                            "count": 11340,
+                                            "self": 167.35672560799594
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1810000160039635e-06,
+                    "total": 1.244000031874748e-06,
                     "count": 1,
-                    "self": 1.1810000160039635e-06
+                    "self": 1.244000031874748e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.10118396200005009,
+                    "total": 0.09417397300012453,
                     "count": 1,
-                    "self": 0.0019062750000102824,
+                    "self": 0.002133608999884018,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.0992776870000398,
+                            "total": 0.09204036400024052,
                             "count": 1,
-                            "self": 0.0992776870000398
+                            "self": 0.09204036400024052
                         }
                     }
                 }

run_logs/training_status.json

@@ -18,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-500071.pt"
                 ]
+            },
+            {
+                "steps": 500071,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500071.onnx",
+                "reward": null,
+                "creation_time": 1666820381.1723173,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-500071.pt"
+                ]
+            },
+            {
+                "steps": 999913,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999913.onnx",
+                "reward": 1.6203333139419556,
+                "creation_time": 1666821515.3680747,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999913.pt"
+                ]
+            },
+            {
+                "steps": 1000041,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000041.onnx",
+                "reward": 1.6203333139419556,
+                "creation_time": 1666821515.4788063,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000041.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500071,
+            "steps": 1000041,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": -0.9994000494480133,
-            "creation_time": 1666819880.3979502,
+            "reward": 1.6203333139419556,
+            "creation_time": 1666821515.4788063,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-500071.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000041.pt"
             ]
         }
     },