3 million training steps

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cebe3c51abef09e4dab48e1bce5da93584bf687a63b7e2c6ea444a9005f5370c
+oid sha256:b926eaf2caaeb26fd4befcbd84ddba118e2330853d9b8e7121692f49c84661d1
 size 1418184

Pyramids/Pyramids-1499964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eab33fe3e6986dba003d85f00cb2d3a9fb9b806730fdd0cec51e8e629d0a65d
+size 1418184

Pyramids/Pyramids-1499964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a526802d1676a720015a4d06d91f0c666fdb6f33e37436aae2ed092d38f76cd5
+size 8650990

Pyramids/Pyramids-1999973.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4024a9db11f25677b3619022094798048615da40fe9ce58eefba1b5d5aa7fd55
+size 1418184

Pyramids/Pyramids-1999973.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f4a15a156319beda748a9f0a0330f6f08c830577dfe43176c3130acb96a0e0
+size 8650990

Pyramids/Pyramids-2499922.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cea5cd2adc75f056f963bc205ae1bd86ee829d0044d521db8f6ce8162dd7d10
+size 1418184

Pyramids/Pyramids-2499922.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad90b64997cde6cb9ae0ae453a3be77b159958cb0f59bcc08052e9bd151ac9cf
+size 8650990

Pyramids/Pyramids-2999948.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b926eaf2caaeb26fd4befcbd84ddba118e2330853d9b8e7121692f49c84661d1
+size 1418184

Pyramids/Pyramids-2999948.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2a3c78000eff60afce7fe2b874b78843ada2eb2c45124ff9e89c18045f26fa
+size 8650990

Pyramids/Pyramids-3000076.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b926eaf2caaeb26fd4befcbd84ddba118e2330853d9b8e7121692f49c84661d1
+size 1418184

Pyramids/Pyramids-3000076.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9095e2296582aa72cd8cd8c8ac473f92c7259a6230ef7ea8421afa587884367c
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77bd8599cfb7870bdc2e02c7e293367d46565c24232440376cd05caef9effe8c
+oid sha256:9095e2296582aa72cd8cd8c8ac473f92c7259a6230ef7ea8421afa587884367c
 size 8650990

Pyramids/events.out.tfevents.1688307818.sekhmet.26636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0c8f8270946f1e4a027834287120950ece0f767de0e9572dde638652eca35a7
+size 667174

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, "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": "Pyramids1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": "Pyramids1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -80,7 +80,7 @@ checkpoint_settings:
   run_id: Pyramids1
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/home/magnus/src/huggingface-reinforcement-learning-course/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/home/magnus/src/huggingface-reinforcement-learning-course/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 192.168.1.111
-Multi-casting "[IP] 192.168.1.111 [Port] 55351 [Flags] 2 [Guid] 427395028 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.111) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 192.168.1.111 [Port] 55309 [Flags] 2 [Guid] 4058568002 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.111) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -17,7 +17,7 @@ Forced to initialize FMOD to to the device driver's system output rate 48000, th
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.080 seconds
+- Completed reload, in  0.086 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)
@@ -49,7 +49,7 @@ 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: 0.556863 ms
+UnloadTime: 0.507405 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 6 worker threads for Enlighten.
@@ -57,7 +57,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 8584 frames, [32.0 KB-64.0 KB]: 7890 frames, [64.0 KB-128.0 KB]: 2291 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 9905 frames, [32.0 KB-64.0 KB]: 18256 frames, [64.0 KB-128.0 KB]: 9357 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
@@ -112,6 +112,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -142,11 +147,6 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 320.0 KB
       Peak Allocated Bytes 251.6 KB
       Overflow Count 4
-    [ALLOC_TEMP_Background Job.Worker 2]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
@@ -155,7 +155,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 3]
       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_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -180,7 +180,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 2]
       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 0]
       Initial Block Size 32.0 KB
@@ -238,28 +238,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 150 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 80 frames, [1.0 MB-2.0 MB]: 37439 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 12451
+  Peak main deferred allocation count 1806
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18764 frames, [32.0 MB-64.0 MB]: 1 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37518 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 32.6 MB
+      Peak Block count 2
+      Peak Allocated memory 24.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18766 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37519 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 25.3 MB
+      Peak Allocated memory 26.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -286,15 +286,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18765 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37518 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]: 18766 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37519 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -304,15 +304,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 79 frames, [1.0 MB-2.0 MB]: 37440 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]: 18765 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37518 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
@@ -322,21 +322,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18766 frames
+      Peak usage frame count: [0-1.0 KB]: 37519 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]: 18766 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37519 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]: 18766 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 37519 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 34.7 KB
@@ -345,4 +345,4 @@ 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":1688307435977,"processId":26325,"allocatedMemory":2004877,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":37399},{"Thread":34740},{"Manager":16203},{"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":3633},{"DynamicArray":30868},{"HashMap":7680},{"Utility":5440},{"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":1688309985451,"processId":26689,"allocatedMemory":2004877,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":37399},{"Thread":34740},{"Manager":16203},{"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":3633},{"DynamicArray":30868},{"HashMap":7680},{"Utility":5440},{"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": 0.7101892232894897,
-            "min": 0.6828570365905762,
-            "max": 1.3821533918380737,
-            "count": 33
+            "value": 0.25150182843208313,
+            "min": 0.23986271023750305,
+            "max": 1.2359827756881714,
+            "count": 67
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 21271.587890625,
-            "min": 20452.93359375,
-            "max": 41929.00390625,
-            "count": 33
+            "value": 7589.3193359375,
+            "min": 7176.6923828125,
+            "max": 37297.015625,
+            "count": 67
         },
         "Pyramids.Step.mean": {
-            "value": 989938.0,
-            "min": 29952.0,
-            "max": 989938.0,
-            "count": 33
+            "value": 2999948.0,
+            "min": 1019935.0,
+            "max": 2999948.0,
+            "count": 67
         },
         "Pyramids.Step.sum": {
-            "value": 989938.0,
-            "min": 29952.0,
-            "max": 989938.0,
-            "count": 33
+            "value": 2999948.0,
+            "min": 1019935.0,
+            "max": 2999948.0,
+            "count": 67
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.4542144238948822,
-            "min": -0.10170693695545197,
-            "max": 0.4712619483470917,
-            "count": 33
+            "value": 0.7547377347946167,
+            "min": -0.07056643068790436,
+            "max": 0.7929686307907104,
+            "count": 67
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 120.82103729248047,
-            "min": -24.409664154052734,
-            "max": 127.24072265625,
-            "count": 33
+            "value": 223.40237426757812,
+            "min": -17.077075958251953,
+            "max": 235.17056274414062,
+            "count": 67
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 10.545604705810547,
-            "min": -0.5143736600875854,
-            "max": 10.545604705810547,
-            "count": 33
+            "value": 0.010818109847605228,
+            "min": -2.4031267166137695,
+            "max": 14.60046100616455,
+            "count": 67
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 2805.130859375,
-            "min": -135.79464721679688,
-            "max": 2805.130859375,
-            "count": 33
+            "value": 3.202160596847534,
+            "min": -636.8285522460938,
+            "max": 4000.5263671875,
+            "count": 67
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 239.45238095238096,
+            "min": 228.2983870967742,
+            "max": 963.4545454545455,
+            "count": 67
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30171.0,
+            "min": 15966.0,
+            "max": 33959.0,
+            "count": 67
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.728792051237727,
+            "min": -0.7822242909760186,
+            "max": 1.7543903112171157,
+            "count": 67
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 217.8277984559536,
+            "min": -25.890001580119133,
+            "max": 217.8277984559536,
+            "count": 67
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.728792051237727,
+            "min": -0.7822242909760186,
+            "max": 1.7543903112171157,
+            "count": 67
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 217.8277984559536,
+            "min": -25.890001580119133,
+            "max": 217.8277984559536,
+            "count": 67
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.012760552965725461,
+            "min": 0.012408850353758974,
+            "max": 0.05711968737580862,
+            "count": 67
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.6078296736814082,
+            "min": 0.7649297210737132,
+            "max": 2.7060816152661573,
+            "count": 67
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06809346485036458,
-            "min": 0.06538149503781003,
-            "max": 0.07446056162705343,
-            "count": 33
+            "value": 0.06908763900606169,
+            "min": 0.06241923725938962,
+            "max": 0.07235957070601731,
+            "count": 67
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9533085079051041,
-            "min": 0.501380954626225,
-            "max": 1.063702930424673,
-            "count": 33
+            "value": 1.0363145850909252,
+            "min": 0.621586629538797,
+            "max": 1.0627095143136103,
+            "count": 67
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 7.669134031652527,
-            "min": 0.0005040609098984665,
-            "max": 7.669134031652527,
-            "count": 33
+            "value": 0.015010668305654286,
+            "min": 0.004781421934297236,
+            "max": 13.36772389532555,
+            "count": 67
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 107.36787644313539,
-            "min": 0.004536548189086199,
-            "max": 107.36787644313539,
-            "count": 33
+            "value": 0.2251600245848143,
+            "min": 0.0669399070801613,
+            "max": 187.1481345345577,
+            "count": 67
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.36274040292857e-06,
-            "min": 7.36274040292857e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 1.4910795030066681e-06,
+            "min": 1.4910795030066681e-06,
+            "max": 0.00019893701146545185,
+            "count": 67
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010307836564099997,
-            "min": 0.00010307836564099997,
-            "max": 0.0031372460542514005,
-            "count": 33
+            "value": 2.236619254510002e-05,
+            "min": 2.236619254510002e-05,
+            "max": 0.0028576116474629664,
+            "count": 67
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1024542142857143,
-            "min": 0.1024542142857143,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10049699333333333,
+            "min": 0.10049699333333333,
+            "max": 0.16631232592592593,
+            "count": 67
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4343590000000002,
-            "min": 1.3886848,
-            "max": 2.4435300000000004,
-            "count": 33
+            "value": 1.5074549,
+            "min": 1.4212187,
+            "max": 2.4525370333333334,
+            "count": 67
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025517600714285713,
-            "min": 0.00025517600714285713,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 5.964963400000005e-05,
+            "min": 5.964963400000005e-05,
+            "max": 0.006634601360000001,
+            "count": 67
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0035724641,
-            "min": 0.0035724641,
-            "max": 0.10460028514,
-            "count": 33
+            "value": 0.0008947445100000008,
+            "min": 0.0008947445100000008,
+            "max": 0.09530844963,
+            "count": 67
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.008357273414731026,
-            "min": 0.008357273414731026,
-            "max": 0.4710610806941986,
-            "count": 33
+            "value": 0.0050939214415848255,
+            "min": 0.002439801814034581,
+            "max": 0.008640534244477749,
+            "count": 67
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.11700183153152466,
-            "min": 0.11700183153152466,
-            "max": 3.2974276542663574,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 401.15277777777777,
-            "min": 401.15277777777777,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28883.0,
-            "min": 15984.0,
-            "max": 35036.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.5154749784204695,
-            "min": -1.0000000521540642,
-            "max": 1.5359694191979036,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 109.1141984462738,
-            "min": -31.999601677060127,
-            "max": 110.58979818224907,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.5154749784204695,
-            "min": -1.0000000521540642,
-            "max": 1.5359694191979036,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 109.1141984462738,
-            "min": -31.999601677060127,
-            "max": 110.58979818224907,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.03484486890665216,
-            "min": 0.03484486890665216,
-            "max": 9.887571858242154,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 2.5088305612789554,
-            "min": 2.5088305612789554,
-            "max": 158.20114973187447,
-            "count": 33
+            "value": 0.07640881836414337,
+            "min": 0.034157223999500275,
+            "max": 0.12960802018642426,
+            "count": 67
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1688306418",
+        "start_time_seconds": "1688307813",
         "python_version": "3.10.12 (main, Jun  9 2023, 20:10:04) [GCC 13.1.1 20230522 [revision dd36656ada05731c069ecd5b1878380294fb1f3e]]",
-        "command_line_arguments": "/home/magnus/.local/venv/ml-agents/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics",
+        "command_line_arguments": "/home/magnus/.local/venv/ml-agents/bin/mlagents-learn --resume config/ppo/PyramidsRND.yaml --env training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1688307436"
+        "end_time_seconds": "1688309985"
     },
-    "total": 1017.4081767249991,
+    "total": 2172.1748791690006,
     "count": 1,
-    "self": 0.2687973769989185,
+    "self": 0.36911092800073675,
     "children": {
         "run_training.setup": {
-            "total": 0.007430470001054346,
+            "total": 0.00738377999914519,
             "count": 1,
-            "self": 0.007430470001054346
+            "self": 0.00738377999914519
         },
         "TrainerController.start_learning": {
-            "total": 1017.1319488779991,
+            "total": 2171.7983844610008,
             "count": 1,
-            "self": 0.92105528805223,
+            "self": 1.9695416254762677,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.8034735409983114,
+                    "total": 6.073836388000927,
                     "count": 1,
-                    "self": 2.8034735409983114
+                    "self": 6.073836388000927
                 },
                 "TrainerController.advance": {
-                    "total": 1013.3518407349475,
-                    "count": 63484,
-                    "self": 0.8775164839626086,
+                    "total": 2163.6984990875244,
+                    "count": 129457,
+                    "self": 1.9047759958630195,
                     "children": {
                         "env_step": {
-                            "total": 663.3966337098991,
-                            "count": 63484,
-                            "self": 595.634598108194,
+                            "total": 1454.348816122112,
+                            "count": 129457,
+                            "self": 1316.3867875059732,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 67.17043835779987,
-                                    "count": 63484,
-                                    "self": 2.5275770016323804,
+                                    "total": 136.72278414898938,
+                                    "count": 129457,
+                                    "self": 5.218426685016311,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 64.64286135616749,
-                                            "count": 62552,
-                                            "self": 64.64286135616749
+                                            "total": 131.50435746397307,
+                                            "count": 125062,
+                                            "self": 131.50435746397307
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.5915972439051984,
-                                    "count": 63484,
+                                    "total": 1.2392444671495468,
+                                    "count": 129457,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1015.9412606569986,
-                                            "count": 63484,
+                                            "total": 2169.3375711670924,
+                                            "count": 129457,
                                             "is_parallel": true,
-                                            "self": 481.71195437502865,
+                                            "self": 981.2120239229353,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0010235270001430763,
+                                                            "total": 0.001912709998578066,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00028448799639591016,
+                                                            "self": 0.00035811499947158154,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0007390390037471661,
+                                                                    "total": 0.0015545949991064845,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007390390037471661
+                                                                    "self": 0.0015545949991064845
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.02386063799895055,
+                                                            "total": 0.021976440000798902,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0002047219986707205,
+                                                            "self": 0.00020695800048997626,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0001814480001485208,
+                                                                    "total": 0.0001730149997456465,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0001814480001485208
+                                                                    "self": 0.0001730149997456465
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.022755512000003364,
+                                                                    "total": 0.02092029800041928,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.022755512000003364
+                                                                    "self": 0.02092029800041928
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.000718956000127946,
+                                                                    "total": 0.0006761690001440002,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0001529119981569238,
+                                                                    "self": 0.00014743599967914633,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005660440019710222,
+                                                                            "total": 0.0005287330004648538,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005660440019710222
+                                                                            "self": 0.0005287330004648538
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 534.2293062819699,
-                                                    "count": 63483,
+                                                    "total": 1188.1255472441571,
+                                                    "count": 129456,
                                                     "is_parallel": true,
-                                                    "self": 18.92074794833934,
+                                                    "self": 38.17118912143269,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 9.88949127784872,
-                                                            "count": 63483,
+                                                            "total": 19.108109347025675,
+                                                            "count": 129456,
                                                             "is_parallel": true,
-                                                            "self": 9.88949127784872
+                                                            "self": 19.108109347025675
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 454.20672625901716,
-                                                            "count": 63483,
+                                                            "total": 1025.0177220240184,
+                                                            "count": 129456,
                                                             "is_parallel": true,
-                                                            "self": 454.20672625901716
+                                                            "self": 1025.0177220240184
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 51.21234079676469,
-                                                            "count": 63483,
+                                                            "total": 105.82852675168033,
+                                                            "count": 129456,
                                                             "is_parallel": true,
-                                                            "self": 9.771190236564507,
+                                                            "self": 20.39225625698782,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 41.441150560200185,
-                                                                    "count": 507864,
+                                                                    "total": 85.43627049469251,
+                                                                    "count": 1035648,
                                                                     "is_parallel": true,
-                                                                    "self": 41.441150560200185
+                                                                    "self": 85.43627049469251
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 349.07769054108576,
-                            "count": 63484,
-                            "self": 1.4452740754513798,
+                            "total": 707.4449069695493,
+                            "count": 129457,
+                            "self": 3.2045918964086013,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 60.25647287764696,
-                                    "count": 63484,
-                                    "self": 60.133807641645035,
+                                    "total": 128.41997512312264,
+                                    "count": 129457,
+                                    "self": 128.17507259811828,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.12266523600192158,
-                                            "count": 2,
-                                            "self": 0.12266523600192158
+                                            "total": 0.24490252500436327,
+                                            "count": 4,
+                                            "self": 0.24490252500436327
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 287.3759435879874,
-                                    "count": 443,
-                                    "self": 185.39682451905537,
+                                    "total": 575.820339950018,
+                                    "count": 945,
+                                    "self": 372.8879248711728,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 101.97911906893205,
-                                            "count": 22881,
-                                            "self": 101.97911906893205
+                                            "total": 202.93241507884522,
+                                            "count": 45537,
+                                            "self": 202.93241507884522
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 6.390000635292381e-07,
+                    "total": 6.009995558997616e-07,
                     "count": 1,
-                    "self": 6.390000635292381e-07
+                    "self": 6.009995558997616e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.055578675001015654,
+                    "total": 0.056506758999603335,
                     "count": 1,
-                    "self": 0.0005947400004515657,
+                    "self": 0.0007781290005368646,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.05498393500056409,
+                            "total": 0.05572862999906647,
                             "count": 1,
-                            "self": 0.05498393500056409
+                            "self": 0.05572862999906647
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499907,
-                "file_path": "results/Pyramids1/Pyramids/Pyramids-499907.onnx",
-                "reward": -0.999700054526329,
-                "creation_time": 1688306916.3121686,
+                "steps": 1499964,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-1499964.onnx",
+                "reward": 0.16919998079538345,
+                "creation_time": 1688308375.1250827,
                 "auxillary_file_paths": [
-                    "results/Pyramids1/Pyramids/Pyramids-499907.pt"
+                    "results/Pyramids1/Pyramids/Pyramids-1499964.pt"
                 ]
             },
             {
-                "steps": 999958,
-                "file_path": "results/Pyramids1/Pyramids/Pyramids-999958.onnx",
-                "reward": 1.7439999878406525,
-                "creation_time": 1688307435.6868505,
+                "steps": 1999973,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-1999973.onnx",
+                "reward": null,
+                "creation_time": 1688308898.380308,
                 "auxillary_file_paths": [
-                    "results/Pyramids1/Pyramids/Pyramids-999958.pt"
+                    "results/Pyramids1/Pyramids/Pyramids-1999973.pt"
                 ]
             },
             {
-                "steps": 1000086,
-                "file_path": "results/Pyramids1/Pyramids/Pyramids-1000086.onnx",
-                "reward": 1.7439999878406525,
-                "creation_time": 1688307435.7487805,
+                "steps": 2499922,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-2499922.onnx",
+                "reward": 1.8329999521374702,
+                "creation_time": 1688309441.457185,
                 "auxillary_file_paths": [
-                    "results/Pyramids1/Pyramids/Pyramids-1000086.pt"
+                    "results/Pyramids1/Pyramids/Pyramids-2499922.pt"
+                ]
+            },
+            {
+                "steps": 2999948,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-2999948.onnx",
+                "reward": 1.545999988913536,
+                "creation_time": 1688309985.0642164,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-2999948.pt"
+                ]
+            },
+            {
+                "steps": 3000076,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-3000076.onnx",
+                "reward": 1.545999988913536,
+                "creation_time": 1688309985.1272125,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-3000076.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000086,
+            "steps": 3000076,
             "file_path": "results/Pyramids1/Pyramids.onnx",
-            "reward": 1.7439999878406525,
-            "creation_time": 1688307435.7487805,
+            "reward": 1.545999988913536,
+            "creation_time": 1688309985.1272125,
             "auxillary_file_paths": [
-                "results/Pyramids1/Pyramids/Pyramids-1000086.pt"
+                "results/Pyramids1/Pyramids/Pyramids-3000076.pt"
             ]
         }
     },