2nd Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b554ead904a56ffeee92d05ff0b10c5cb52f9925507e630cba10e2d9e765d5b2
+oid sha256:d62147cbf4eb4caa9317acd4c85e4ea2349fa58b05a22a2ddb5e28ee21c3a297
 size 1420238

Pyramids/Pyramids-1499980.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62147cbf4eb4caa9317acd4c85e4ea2349fa58b05a22a2ddb5e28ee21c3a297
+size 1420238

Pyramids/Pyramids-1499980.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7b59204b5d45430eaedbdd35fc5f646d14333df4d0354aeb1d38d1d9a0717f
+size 8656252

Pyramids/Pyramids-1500025.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62147cbf4eb4caa9317acd4c85e4ea2349fa58b05a22a2ddb5e28ee21c3a297
+size 1420238

Pyramids/Pyramids-1500025.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b033c69e507164fae6d167392bed8624fa19b598b4523cf778b248c247b40c43
+size 8656252

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4744d325b2a688fee95fbf38c01eefa8657fe688cffef2fcb30f5248eaddb781
+oid sha256:c06641f96beb4f320b09f55fbd2319b6650b352a7fae959db2808b696d762396
 size 8655778

Pyramids/events.out.tfevents.1726704546.fedora.1007416.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6963637d5806251d41abc8adfd7c120337a819eeac7492be1848b1227db13e
+size 1422

Pyramids/events.out.tfevents.1726704575.fedora.1007643.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df56b6c406d86f9f77f15edd54fdab5f0c9e2364d2197745bce334093bcffec3
+size 149410

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 1500000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -82,7 +82,7 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/home/michael/Repo/DeepRLCourse/Unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/home/michael/Repo/DeepRLCourse/Unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 192.168.1.214
-Multi-casting "[IP] 192.168.1.214 [Port] 55503 [Flags] 2 [Guid] 3936719187 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.214) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 192.168.1.214 [Port] 55186 [Flags] 2 [Guid] 1772110907 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.214) [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: /home/michael/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /home/michael/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /home/michael/Repo/DeepRLCourse/Unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -16,7 +13,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.060 seconds
+- Completed reload, in  0.058 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)
@@ -48,7 +45,7 @@ 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: 0.607191 ms
+UnloadTime: 0.561004 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 8 worker threads for Enlighten.
@@ -56,7 +53,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 3716 frames, [32.0 KB-64.0 KB]: 11795 frames, [64.0 KB-128.0 KB]: 3252 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 467 frames, [32.0 KB-64.0 KB]: 6071 frames, [64.0 KB-128.0 KB]: 2848 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
@@ -134,7 +131,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 1]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 10]
       Initial Block Size 256.0 KB
@@ -239,7 +236,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 9]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
@@ -257,28 +254,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 129 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18465 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 38 frames, [1.0 MB-2.0 MB]: 9349 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 13367
+  Peak main deferred allocation count 1802
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.8 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]: 18763 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9386 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 30.4 MB
+      Peak Block count 2
+      Peak Allocated memory 23.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18764 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9387 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 28.7 MB
+      Peak Allocated memory 26.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -305,15 +302,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.8 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18763 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9386 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]: 18764 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 9387 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -323,15 +320,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.8 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]: 18465 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 51 frames, [1.0 MB-2.0 MB]: 9336 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]: 18763 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 9386 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
@@ -341,21 +338,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.8 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18764 frames
+      Peak usage frame count: [0-1.0 KB]: 9387 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]: 18764 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9387 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: [32.0 KB-64.0 KB]: 18764 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 9387 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 38.0 KB
@@ -364,4 +361,4 @@ 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":1726704236856,"processId":994652,"allocatedMemory":2079683,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":108278},{"Thread":34852},{"Manager":18447},{"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":3572},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"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":1726705048687,"processId":1007703,"allocatedMemory":2079683,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":108278},{"Thread":34852},{"Manager":18447},{"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":3572},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"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": 0.29960519075393677,
-            "min": 0.29798299074172974,
-            "max": 1.4560059309005737,
-            "count": 33
+            "value": 0.21720464527606964,
+            "min": 0.20768827199935913,
+            "max": 0.29807475209236145,
+            "count": 17
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 8897.076171875,
-            "min": 8897.076171875,
-            "max": 44169.39453125,
-            "count": 33
+            "value": 6460.53515625,
+            "min": 6210.7099609375,
+            "max": 8664.7734375,
+            "count": 17
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 279.6574074074074,
+            "min": 260.4086956521739,
+            "max": 345.0444444444444,
+            "count": 17
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30203.0,
+            "min": 16795.0,
+            "max": 31320.0,
+            "count": 17
         },
         "Pyramids.Step.mean": {
-            "value": 989934.0,
-            "min": 29952.0,
-            "max": 989934.0,
-            "count": 33
+            "value": 1499980.0,
+            "min": 1019934.0,
+            "max": 1499980.0,
+            "count": 17
         },
         "Pyramids.Step.sum": {
-            "value": 989934.0,
-            "min": 29952.0,
-            "max": 989934.0,
-            "count": 33
+            "value": 1499980.0,
+            "min": 1019934.0,
+            "max": 1499980.0,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5091343522071838,
-            "min": -0.10006243735551834,
-            "max": 0.6429761052131653,
-            "count": 33
+            "value": 0.6857998371124268,
+            "min": 0.5569564700126648,
+            "max": 0.6999236941337585,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 138.99368286132812,
-            "min": -24.115047454833984,
-            "max": 183.8911590576172,
-            "count": 33
+            "value": 197.51034545898438,
+            "min": 106.35494995117188,
+            "max": 207.87733459472656,
+            "count": 17
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.03600286692380905,
-            "min": -0.0009824818698689342,
-            "max": 0.28143277764320374,
-            "count": 33
+            "value": 0.011466632597148418,
+            "min": -0.003921444062143564,
+            "max": 0.08421960473060608,
+            "count": 17
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 9.82878303527832,
-            "min": -0.27607738971710205,
-            "max": 67.82530212402344,
-            "count": 33
+            "value": 3.3023900985717773,
+            "min": -1.0901614427566528,
+            "max": 24.002588272094727,
+            "count": 17
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7042280218311558,
+            "min": 1.502714267716958,
+            "max": 1.7395912886961646,
+            "count": 17
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 182.35239833593369,
+            "min": 99.20499943196774,
+            "max": 200.05299820005894,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7042280218311558,
+            "min": 1.502714267716958,
+            "max": 1.7395912886961646,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 182.35239833593369,
+            "min": 99.20499943196774,
+            "max": 200.05299820005894,
+            "count": 17
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.024416481507300164,
+            "min": 0.022409672142715532,
+            "max": 0.03160340793149042,
+            "count": 17
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.6125635212811176,
+            "min": 1.6711126518785022,
+            "max": 3.0019219083333155,
+            "count": 17
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06654955223720108,
-            "min": 0.06490091154248351,
-            "max": 0.07188743139914651,
-            "count": 33
+            "value": 0.06975638308323964,
+            "min": 0.06622975742485485,
+            "max": 0.07178942280422364,
+            "count": 17
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9982432835580162,
-            "min": 0.5009289087129531,
-            "max": 1.0783114709871977,
-            "count": 33
+            "value": 0.9765893631653549,
+            "min": 0.6101926534708279,
+            "max": 1.01275189212916,
+            "count": 17
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.017488572560574137,
-            "min": 0.00015591603150889535,
-            "max": 0.017706629181269643,
-            "count": 33
+            "value": 0.016813369541307025,
+            "min": 0.01431408897596633,
+            "max": 0.017236776922973582,
+            "count": 17
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.26232858840861206,
-            "min": 0.0017150763465978488,
-            "max": 0.26232858840861206,
-            "count": 33
+            "value": 0.23538717357829836,
+            "min": 0.1338397917764572,
+            "max": 0.24501954557490538,
+            "count": 17
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.439697520133333e-06,
-            "min": 7.439697520133333e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 2.9738561516047628e-06,
+            "min": 2.9738561516047628e-06,
+            "max": 9.789306736899999e-05,
+            "count": 17
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00011159546280199999,
-            "min": 0.00011159546280199999,
-            "max": 0.0032248981250339996,
-            "count": 33
+            "value": 4.1633986122466676e-05,
+            "min": 4.1633986122466676e-05,
+            "max": 0.0013018851660385998,
+            "count": 17
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10247986666666668,
-            "min": 0.10247986666666668,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.1009912523809524,
+            "min": 0.1009912523809524,
+            "max": 0.13263100000000005,
+            "count": 17
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.5371980000000003,
-            "min": 1.3886848,
-            "max": 2.4826252,
-            "count": 33
+            "value": 1.4138775333333335,
+            "min": 1.1936790000000004,
+            "max": 1.9048246000000002,
+            "count": 17
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025773868,
-            "min": 0.00025773868,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.0001090261128571429,
+            "min": 0.0001090261128571429,
+            "max": 0.0032698369000000002,
+            "count": 17
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0038660802,
-            "min": 0.0038660802,
-            "max": 0.10750910340000001,
-            "count": 33
+            "value": 0.0015263655800000005,
+            "min": 0.0015263655800000005,
+            "max": 0.04349274386,
+            "count": 17
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.00960482470691204,
-            "min": 0.00960482470691204,
-            "max": 0.36747294664382935,
-            "count": 33
+            "value": 0.00849104393273592,
+            "min": 0.0080970274284482,
+            "max": 0.009547818452119827,
+            "count": 17
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.14407236874103546,
-            "min": 0.13644836843013763,
-            "max": 2.57231068611145,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 361.9166666666667,
-            "min": 296.02884615384613,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30401.0,
-            "min": 15984.0,
-            "max": 34477.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.5190047413288128,
-            "min": -1.0000000521540642,
-            "max": 1.6462672905853162,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 127.59639827162027,
-            "min": -32.000001668930054,
-            "max": 171.21179822087288,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.5190047413288128,
-            "min": -1.0000000521540642,
-            "max": 1.6462672905853162,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 127.59639827162027,
-            "min": -32.000001668930054,
-            "max": 171.21179822087288,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.036438929173701104,
-            "min": 0.03332296301036828,
-            "max": 6.818625710904598,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 3.060870050590893,
-            "min": 2.8586726340581663,
-            "max": 109.09801137447357,
-            "count": 33
+            "value": 0.11887460947036743,
+            "min": 0.08593036234378815,
+            "max": 0.13323572278022766,
+            "count": 17
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 17
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 17
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1726703349",
+        "start_time_seconds": "1726704575",
         "python_version": "3.10.14 (main, Apr 17 2024, 00:00:00) [GCC 13.2.1 20240316 (Red Hat 13.2.1-7)]",
-        "command_line_arguments": "/home/michael/Repo/DeepRLCourse/venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/home/michael/Repo/DeepRLCourse/venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.0+rocm6.1",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1726704236"
+        "end_time_seconds": "1726705048"
     },
-    "total": 887.1575166250113,
+    "total": 473.71785410499433,
     "count": 1,
-    "self": 0.2180966189771425,
+    "self": 0.21809501701500267,
     "children": {
         "run_training.setup": {
-            "total": 0.017393044021446258,
+            "total": 0.01654465199680999,
             "count": 1,
-            "self": 0.017393044021446258
+            "self": 0.01654465199680999
         },
         "TrainerController.start_learning": {
-            "total": 886.9220269620128,
+            "total": 473.4832144359825,
             "count": 1,
-            "self": 0.8224835708388127,
+            "self": 0.43410689767915756,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.0941993249871302,
+                    "total": 1.1233860200154595,
                     "count": 1,
-                    "self": 1.0941993249871302
+                    "self": 1.1233860200154595
                 },
                 "TrainerController.advance": {
-                    "total": 884.9606371181726,
-                    "count": 63905,
-                    "self": 0.7006779504881706,
+                    "total": 471.8779994753131,
+                    "count": 32645,
+                    "self": 0.3900848307821434,
                     "children": {
                         "env_step": {
-                            "total": 518.1983346254565,
-                            "count": 63905,
-                            "self": 424.1133040448767,
+                            "total": 285.53448172067874,
+                            "count": 32645,
+                            "self": 236.0893001385557,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 93.62509990285616,
-                                    "count": 63905,
-                                    "self": 2.1186361884174403,
+                                    "total": 49.193108400155324,
+                                    "count": 32645,
+                                    "self": 1.0925407735048793,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 91.50646371443872,
-                                            "count": 62544,
-                                            "self": 91.50646371443872
+                                            "total": 48.100567626650445,
+                                            "count": 31290,
+                                            "self": 48.100567626650445
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.4599306777236052,
-                                    "count": 63905,
+                                    "total": 0.25207318196771666,
+                                    "count": 32645,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 885.8882342684374,
-                                            "count": 63905,
+                                            "total": 472.8673126748181,
+                                            "count": 32645,
                                             "is_parallel": true,
-                                            "self": 511.2588778018544,
+                                            "self": 262.82770341748255,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0012412260111887008,
+                                                            "total": 0.0011030320019926876,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004222939896862954,
+                                                            "self": 0.0003565579536370933,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0008189320215024054,
+                                                                    "total": 0.0007464740483555943,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008189320215024054
+                                                                    "self": 0.0007464740483555943
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.01749929101788439,
+                                                            "total": 0.016810662986245006,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00020434203906916082,
+                                                            "self": 0.00019693400827236474,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00019087400869466364,
+                                                                    "total": 0.0001981329987756908,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00019087400869466364
+                                                                    "self": 0.0001981329987756908
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.016459746984764934,
+                                                                    "total": 0.015795077983057126,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.016459746984764934
+                                                                    "self": 0.015795077983057126
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0006443279853556305,
+                                                                    "total": 0.0006205179961398244,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000153744884300977,
+                                                                    "self": 0.0001533749746158719,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0004905831010546535,
+                                                                            "total": 0.0004671430215239525,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0004905831010546535
+                                                                            "self": 0.0004671430215239525
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 374.629356466583,
-                                                    "count": 63904,
+                                                    "total": 210.03960925733554,
+                                                    "count": 32644,
                                                     "is_parallel": true,
-                                                    "self": 11.14457219367614,
+                                                    "self": 5.756008195952745,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 8.425960593507625,
-                                                            "count": 63904,
+                                                            "total": 4.313196824630722,
+                                                            "count": 32644,
                                                             "is_parallel": true,
-                                                            "self": 8.425960593507625
+                                                            "self": 4.313196824630722
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 321.298151894327,
-                                                            "count": 63904,
+                                                            "total": 182.56862023012945,
+                                                            "count": 32644,
                                                             "is_parallel": true,
-                                                            "self": 321.298151894327
+                                                            "self": 182.56862023012945
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 33.76067178507219,
-                                                            "count": 63904,
+                                                            "total": 17.40178400662262,
+                                                            "count": 32644,
                                                             "is_parallel": true,
-                                                            "self": 7.647785081062466,
+                                                            "self": 4.037765364308143,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 26.112886704009725,
-                                                                    "count": 511232,
+                                                                    "total": 13.364018642314477,
+                                                                    "count": 261152,
                                                                     "is_parallel": true,
-                                                                    "self": 26.112886704009725
+                                                                    "self": 13.364018642314477
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 366.06162454222795,
-                            "count": 63905,
-                            "self": 1.439498271647608,
+                            "total": 185.95343292385223,
+                            "count": 32645,
+                            "self": 0.8427105708105955,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 68.70457745151361,
-                                    "count": 63905,
-                                    "self": 68.60814581354498,
+                                    "total": 36.69104316688026,
+                                    "count": 32645,
+                                    "self": 36.632464149879524,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.09643163796863519,
-                                            "count": 2,
-                                            "self": 0.09643163796863519
+                                            "total": 0.05857901700073853,
+                                            "count": 1,
+                                            "self": 0.05857901700073853
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 295.9175488190667,
-                                    "count": 441,
-                                    "self": 163.14153040383826,
+                                    "total": 148.41967918616137,
+                                    "count": 236,
+                                    "self": 82.20424556016224,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 132.77601841522846,
-                                            "count": 22827,
-                                            "self": 132.77601841522846
+                                            "total": 66.21543362599914,
+                                            "count": 11352,
+                                            "self": 66.21543362599914
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 7.00005330145359e-07,
+                    "total": 5.599868018180132e-07,
                     "count": 1,
-                    "self": 7.00005330145359e-07
+                    "self": 5.599868018180132e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0447062480088789,
+                    "total": 0.04772148298798129,
                     "count": 1,
-                    "self": 0.0007648440077900887,
+                    "self": 0.0014789959823247045,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.04394140400108881,
+                            "total": 0.046242487005656585,
                             "count": 1,
-                            "self": 0.04394140400108881
+                            "self": 0.046242487005656585
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499936,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499936.onnx",
-                "reward": 1.782499983906746,
-                "creation_time": 1726703781.089745,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499936.pt"
-                ]
-            },
             {
                 "steps": 999881,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-999881.onnx",
@@ -27,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000009.pt"
                 ]
+            },
+            {
+                "steps": 1000009,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000009.onnx",
+                "reward": null,
+                "creation_time": 1726704547.1820679,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000009.pt"
+                ]
+            },
+            {
+                "steps": 1499980,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499980.onnx",
+                "reward": 1.779750008136034,
+                "creation_time": 1726705048.464142,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499980.pt"
+                ]
+            },
+            {
+                "steps": 1500025,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1500025.onnx",
+                "reward": 1.7125999957323075,
+                "creation_time": 1726705048.514016,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1500025.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000009,
+            "steps": 1500025,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.8056666205326717,
-            "creation_time": 1726704236.6866086,
+            "reward": 1.7125999957323075,
+            "creation_time": 1726705048.514016,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000009.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1500025.pt"
             ]
         }
     },