Fourth Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0adc9192d85ff6a2533fdaf2fea8fe24d9bcd5379782428d8acf7c5f004e1e3
+oid sha256:520636e308bc5353d3da672c4e7424a3a1e4cfd88ab406b047a17f4f6ad8d396
 size 2471803

Pyramids/Pyramids-1199979.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58b5fbcc35dabb2bfc94a53953723c924741608c4db79ab90fb1e3340dc58829
+size 2471803

Pyramids/Pyramids-1199979.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1007f24e35ee054d4ed8d33b0bfc97c579efcbae41981758f0db0f3e64984b2
+size 19720601

Pyramids/Pyramids-1599944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8a10ad5b9565c8c037320e156d568d2a127881c7097bcdb76fb9164cf9409c
+size 2471803

Pyramids/Pyramids-1599944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d120df3fcabd369bf6f3715bccefc1f76c1c5048ab3101464a80a743b51ff4cf
+size 19720601

Pyramids/Pyramids-1999959.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520636e308bc5353d3da672c4e7424a3a1e4cfd88ab406b047a17f4f6ad8d396
+size 2471803

Pyramids/Pyramids-1999959.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca39e954e6520fa24ca069998fc5d58845a7cee87810b343d4c40bcd3a69945c
+size 19720601

Pyramids/Pyramids-2000026.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520636e308bc5353d3da672c4e7424a3a1e4cfd88ab406b047a17f4f6ad8d396
+size 2471803

Pyramids/Pyramids-2000026.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbbb45485535e947e6900bce30c0daac396660355f308f8026c7d1628d35b716
+size 19720601

Pyramids/Pyramids-799993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8b974caa8c9571cd53518e96b9a39ced2b83761f1e3922fed7ee52d4481155
+size 2471803

Pyramids/Pyramids-799993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1faa71562587523f87ef26951796af6e730786d62b96184d5871797648335cf1
+size 19720508

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf6e9bbf566d5eb29188f2793409833667c6cf003c004469a7d0fed4289f90f
+oid sha256:bbfad4168a726a2bb2d12cdb4ea5cbb09e818a630dd55b212324c2c795495fd6
 size 19720043

Pyramids/events.out.tfevents.1697030933.429c7995e803.37102.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4413ff6176dde2c7cfdc968736ebbb15e954371b50d593ddbcf7751f4e23a662
+size 628450

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.001, "epsilon": 0.1, "lambd": 0.9, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "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": 512, "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": true, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training6", "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": 0.001, "epsilon": 0.1, "lambd": 0.9, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 400000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "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": 512, "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": true, "max_steps": 2000000, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training7", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -14,7 +14,7 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 200000
+    checkpoint_interval: 400000
     network_settings:
       normalize: false
       hidden_units: 512
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: true
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -78,7 +78,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training6
+  run_id: Pyramids Training7
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55103 [Flags] 2 [Guid] 1664730719 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55023 [Flags] 2 [Guid] 2408970280 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +33,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.088 seconds
+- Completed reload, in  0.144 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)
@@ -65,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.747120 ms
+UnloadTime: 0.980195 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 2958 frames, [32.0 KB-64.0 KB]: 11615 frames, [64.0 KB-128.0 KB]: 4198 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 9686 frames, [32.0 KB-64.0 KB]: 17700 frames, [64.0 KB-128.0 KB]: 10129 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
@@ -123,7 +123,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -133,7 +133,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -146,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -204,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18473 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37217 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 13352
+  Peak main deferred allocation count 12584
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18771 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37514 frames, [32.0 MB-64.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.1 MB
+      Peak Allocated memory 32.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18772 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37516 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.9 MB
+      Peak Allocated memory 21.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18771 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37515 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]: 18772 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37516 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,16 +272,16 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18473 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37217 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]: 18771 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37515 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
-      Peak Allocated memory 4.7 MB
+      Peak Block count 1
+      Peak Allocated memory 3.9 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -290,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18772 frames
+      Peak usage frame count: [0-1.0 KB]: 37516 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]: 18772 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37516 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18772 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37516 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 29.0 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1697030676623,"processId":26030,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1697035812161,"processId":37123,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.19224198162555695,
-            "min": 0.19224198162555695,
-            "max": 1.570914626121521,
-            "count": 33
+            "value": 0.10838235914707184,
+            "min": 0.09950023889541626,
+            "max": 1.5246258974075317,
+            "count": 66
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 5813.3974609375,
-            "min": 5813.3974609375,
-            "max": 47655.265625,
-            "count": 33
+            "value": 3287.88720703125,
+            "min": 2981.8232421875,
+            "max": 46251.05078125,
+            "count": 66
         },
         "Pyramids.Step.mean": {
-            "value": 989958.0,
+            "value": 1979902.0,
             "min": 29952.0,
-            "max": 989958.0,
-            "count": 33
+            "max": 1979902.0,
+            "count": 66
         },
         "Pyramids.Step.sum": {
-            "value": 989958.0,
+            "value": 1979902.0,
             "min": 29952.0,
-            "max": 989958.0,
-            "count": 33
+            "max": 1979902.0,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7307552695274353,
-            "min": -0.05546841025352478,
-            "max": 0.7307552695274353,
-            "count": 33
+            "value": 0.78346186876297,
+            "min": -0.0348844900727272,
+            "max": 0.8182347416877747,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 216.30355834960938,
-            "min": -13.367886543273926,
-            "max": 216.30355834960938,
-            "count": 33
+            "value": 231.12124633789062,
+            "min": -8.407161712646484,
+            "max": 246.28866577148438,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.03569478541612625,
-            "min": 0.03569478541612625,
-            "max": 0.9827675223350525,
-            "count": 33
+            "value": 0.03988979011774063,
+            "min": 0.027765318751335144,
+            "max": 0.8566910624504089,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 10.565656661987305,
-            "min": 10.565656661987305,
-            "max": 232.91590881347656,
-            "count": 33
+            "value": 11.767488479614258,
+            "min": 8.19076919555664,
+            "max": 203.03578186035156,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06640867602770228,
-            "min": 0.06514035453114451,
-            "max": 0.07432111201342195,
-            "count": 33
+            "value": 0.06973337994090148,
+            "min": 0.06298405039318217,
+            "max": 0.07285490355130575,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9961301404155343,
-            "min": 0.48186746976490874,
-            "max": 1.0994104182281457,
-            "count": 33
+            "value": 0.9762673191726207,
+            "min": 0.4944924081544574,
+            "max": 1.0610899953559663,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.00941091305469741,
-            "min": 0.0003484809830390088,
-            "max": 0.042529660542911386,
-            "count": 33
+            "value": 0.009280893576596144,
+            "min": 0.0011239011363729627,
+            "max": 0.03225873692536089,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.14116369582046115,
-            "min": 0.0027878478643120702,
-            "max": 0.2977076238003797,
-            "count": 33
+            "value": 0.12993251007234602,
+            "min": 0.010115110227356665,
+            "max": 0.22581115847752622,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.4923975025666634e-06,
-            "min": 7.4923975025666634e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 5.1515804256964275e-06,
+            "min": 5.1515804256964275e-06,
+            "max": 0.0002975753150939428,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00011238596253849996,
-            "min": 0.00011238596253849996,
-            "max": 0.0036341581886139987,
-            "count": 33
+            "value": 7.212212595974998e-05,
+            "min": 7.212212595974998e-05,
+            "max": 0.0039795245234918505,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10000000000000002,
-            "min": 0.09999999999999998,
+            "value": 0.1,
+            "min": 0.09999999999999996,
             "max": 0.10000000000000002,
-            "count": 33
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.5000000000000002,
-            "min": 0.6999999999999998,
+            "value": 1.4000000000000001,
+            "min": 0.7,
             "max": 1.5000000000000002,
-            "count": 33
+            "count": 66
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 3.4724589999999995e-05,
-            "min": 3.4724589999999995e-05,
-            "max": 0.0009839970742857144,
-            "count": 33
+            "value": 2.699989107142857e-05,
+            "min": 2.699989107142857e-05,
+            "max": 0.0009919985371428571,
+            "count": 66
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0005208688499999999,
-            "min": 0.0005208688499999999,
-            "max": 0.0121327214,
-            "count": 33
+            "value": 0.000377998475,
+            "min": 0.000377998475,
+            "max": 0.013272430685000001,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.04988045617938042,
-            "min": 0.04988045617938042,
-            "max": 0.9820275902748108,
-            "count": 33
+            "value": 0.04242420941591263,
+            "min": 0.04242420941591263,
+            "max": 1.0313241481781006,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.7482068538665771,
-            "min": 0.7323045134544373,
-            "max": 6.87419319152832,
-            "count": 33
+            "value": 0.593938946723938,
+            "min": 0.593938946723938,
+            "max": 7.219268798828125,
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 255.9145299145299,
-            "min": 255.9145299145299,
+            "value": 229.6124031007752,
+            "min": 215.93939393939394,
             "max": 999.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29942.0,
+            "value": 29620.0,
             "min": 15984.0,
-            "max": 32018.0,
-            "count": 33
+            "max": 33105.0,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.726989729791625,
+            "value": 1.7548759521324506,
             "min": -1.0000000521540642,
-            "max": 1.726989729791625,
-            "count": 33
+            "max": 1.7840605914366967,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 202.05779838562012,
-            "min": -32.000001668930054,
-            "max": 202.05779838562012,
-            "count": 33
+            "value": 226.37899782508612,
+            "min": -28.205001778900623,
+            "max": 239.27799846231937,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.726989729791625,
+            "value": 1.7548759521324506,
             "min": -1.0000000521540642,
-            "max": 1.726989729791625,
-            "count": 33
+            "max": 1.7840605914366967,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 202.05779838562012,
-            "min": -32.000001668930054,
-            "max": 202.05779838562012,
-            "count": 33
+            "value": 226.37899782508612,
+            "min": -28.205001778900623,
+            "max": 239.27799846231937,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.1326896303251752,
-            "min": 0.1326896303251752,
-            "max": 40.02039594389498,
-            "count": 33
+            "value": 0.10055353927657065,
+            "min": 0.09892512742027809,
+            "max": 39.71318576578051,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 15.524686748045497,
-            "min": 15.524686748045497,
-            "max": 640.3263351023197,
-            "count": 33
+            "value": 12.971406566677615,
+            "min": 12.971406566677615,
+            "max": 635.4109722524881,
+            "count": 66
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1697028329",
+        "start_time_seconds": "1697030931",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training6 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training7 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.0.1+cu118",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1697030676"
+        "end_time_seconds": "1697035812"
     },
-    "total": 2346.7568116869998,
+    "total": 4880.286503290001,
     "count": 1,
-    "self": 1.0405180459993062,
+    "self": 0.47867501100154186,
     "children": {
         "run_training.setup": {
-            "total": 0.043942708999566094,
+            "total": 0.06616394900083833,
             "count": 1,
-            "self": 0.043942708999566094
+            "self": 0.06616394900083833
         },
         "TrainerController.start_learning": {
-            "total": 2345.672350932001,
+            "total": 4879.7416643299985,
             "count": 1,
-            "self": 1.3403733387622196,
+            "self": 2.922324561943242,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.42468070599989,
+                    "total": 4.117271718001575,
                     "count": 1,
-                    "self": 3.42468070599989
+                    "self": 4.117271718001575
                 },
                 "TrainerController.advance": {
-                    "total": 2340.7143047812388,
-                    "count": 64446,
-                    "self": 1.344616622475769,
+                    "total": 4872.580148277055,
+                    "count": 129796,
+                    "self": 2.95847217220944,
                     "children": {
                         "env_step": {
-                            "total": 1702.8825311429227,
-                            "count": 64446,
-                            "self": 1577.4343140297942,
+                            "total": 3585.0640847292016,
+                            "count": 129796,
+                            "self": 3332.4309696495184,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 124.64412061116309,
-                                    "count": 64446,
-                                    "self": 4.402678408201609,
+                                    "total": 250.96996573504111,
+                                    "count": 129796,
+                                    "self": 9.216337606583693,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 120.24144220296148,
-                                            "count": 62572,
-                                            "self": 120.24144220296148
+                                            "total": 241.75362812845742,
+                                            "count": 125053,
+                                            "self": 241.75362812845742
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8040965019654323,
-                                    "count": 64446,
+                                    "total": 1.663149344642079,
+                                    "count": 129796,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2340.758332195177,
-                                            "count": 64446,
+                                            "total": 4870.158710075988,
+                                            "count": 129796,
                                             "is_parallel": true,
-                                            "self": 877.6269186870013,
+                                            "self": 1773.503997150825,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.001989801000490843,
+                                                            "total": 0.002491384000677499,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006273700018937234,
+                                                            "self": 0.0007437559997924836,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013624309985971195,
+                                                                    "total": 0.0017476280008850154,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013624309985971195
+                                                                    "self": 0.0017476280008850154
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07798009999987698,
+                                                            "total": 0.05994438500056276,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000597982999352098,
+                                                            "self": 0.0006097460027376655,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005286890000206768,
+                                                                    "total": 0.00046967599882918876,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005286890000206768
+                                                                    "self": 0.00046967599882918876
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.07509337800001958,
+                                                                    "total": 0.057041281999772764,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.07509337800001958
+                                                                    "self": 0.057041281999772764
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017600500004846253,
+                                                                    "total": 0.0018236809992231429,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00037057199915579986,
+                                                                    "self": 0.00043842700142704416,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013894780013288255,
+                                                                            "total": 0.0013852539977960987,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013894780013288255
+                                                                            "self": 0.0013852539977960987
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1463.1314135081757,
-                                                    "count": 64445,
+                                                    "total": 3096.654712925163,
+                                                    "count": 129795,
                                                     "is_parallel": true,
-                                                    "self": 33.57405870530329,
+                                                    "self": 68.39266053539359,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.955753032837492,
-                                                            "count": 64445,
+                                                            "total": 46.88572312147335,
+                                                            "count": 129795,
                                                             "is_parallel": true,
-                                                            "self": 22.955753032837492
+                                                            "self": 46.88572312147335
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1311.566378843152,
-                                                            "count": 64445,
+                                                            "total": 2787.3074446792943,
+                                                            "count": 129795,
                                                             "is_parallel": true,
-                                                            "self": 1311.566378843152
+                                                            "self": 2787.3074446792943
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 95.03522292688285,
-                                                            "count": 64445,
+                                                            "total": 194.06888458900175,
+                                                            "count": 129795,
                                                             "is_parallel": true,
-                                                            "self": 18.735387731310766,
+                                                            "self": 38.87406657887732,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 76.29983519557209,
-                                                                    "count": 515560,
+                                                                    "total": 155.19481801012444,
+                                                                    "count": 1038360,
                                                                     "is_parallel": true,
-                                                                    "self": 76.29983519557209
+                                                                    "self": 155.19481801012444
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 636.4871570158402,
-                            "count": 64446,
-                            "self": 2.536269047989663,
+                            "total": 1284.5575913756438,
+                            "count": 129796,
+                            "self": 5.444389387534102,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 121.15106498483419,
-                                    "count": 64446,
-                                    "self": 120.47755503783446,
+                                    "total": 246.93835949208733,
+                                    "count": 129796,
+                                    "self": 246.17243289408725,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.6735099469997294,
+                                            "total": 0.7659265980000782,
                                             "count": 5,
-                                            "self": 0.6735099469997294
+                                            "self": 0.7659265980000782
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 512.7998229830164,
-                                    "count": 448,
-                                    "self": 300.0865035119996,
+                                    "total": 1032.1748424960224,
+                                    "count": 931,
+                                    "self": 605.3518582801753,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 212.7133194710168,
-                                            "count": 22815,
-                                            "self": 212.7133194710168
+                                            "total": 426.8229842158471,
+                                            "count": 45573,
+                                            "self": 426.8229842158471
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.5260011423379183e-06,
+                    "total": 1.0879994079004973e-06,
                     "count": 1,
-                    "self": 1.5260011423379183e-06
+                    "self": 1.0879994079004973e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.19299057999887737,
+                    "total": 0.12191868499940028,
                     "count": 1,
-                    "self": 0.005388030000176514,
+                    "self": 0.0018928459994640434,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.18760254999870085,
+                            "total": 0.12002583899993624,
                             "count": 1,
-                            "self": 0.18760254999870085
+                            "self": 0.12002583899993624
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 399945,
-                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-399945.onnx",
-                "reward": 0.984749985858798,
-                "creation_time": 1697029155.0306525,
+                "steps": 799993,
+                "file_path": "results/Pyramids Training7/Pyramids/Pyramids-799993.onnx",
+                "reward": 1.3944999910891056,
+                "creation_time": 1697032733.828133,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training6/Pyramids/Pyramids-399945.pt"
+                    "results/Pyramids Training7/Pyramids/Pyramids-799993.pt"
                 ]
             },
             {
-                "steps": 599946,
-                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-599946.onnx",
-                "reward": 1.7097499668598175,
-                "creation_time": 1697029661.467683,
+                "steps": 1199979,
+                "file_path": "results/Pyramids Training7/Pyramids/Pyramids-1199979.onnx",
+                "reward": 1.783999964594841,
+                "creation_time": 1697033740.4400687,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training6/Pyramids/Pyramids-599946.pt"
+                    "results/Pyramids Training7/Pyramids/Pyramids-1199979.pt"
                 ]
             },
             {
-                "steps": 799906,
-                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-799906.onnx",
-                "reward": null,
-                "creation_time": 1697030162.5838199,
+                "steps": 1599944,
+                "file_path": "results/Pyramids Training7/Pyramids/Pyramids-1599944.onnx",
+                "reward": 1.8012856926236833,
+                "creation_time": 1697034773.5944161,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training6/Pyramids/Pyramids-799906.pt"
+                    "results/Pyramids Training7/Pyramids/Pyramids-1599944.pt"
                 ]
             },
             {
-                "steps": 999901,
-                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-999901.onnx",
-                "reward": 1.704285700406347,
-                "creation_time": 1697030675.4404697,
+                "steps": 1999959,
+                "file_path": "results/Pyramids Training7/Pyramids/Pyramids-1999959.onnx",
+                "reward": 1.6434444271855884,
+                "creation_time": 1697035811.604457,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training6/Pyramids/Pyramids-999901.pt"
+                    "results/Pyramids Training7/Pyramids/Pyramids-1999959.pt"
                 ]
             },
             {
-                "steps": 1000029,
-                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-1000029.onnx",
-                "reward": 1.704285700406347,
-                "creation_time": 1697030675.6403673,
+                "steps": 2000026,
+                "file_path": "results/Pyramids Training7/Pyramids/Pyramids-2000026.onnx",
+                "reward": 1.659699985384941,
+                "creation_time": 1697035811.7303658,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training6/Pyramids/Pyramids-1000029.pt"
+                    "results/Pyramids Training7/Pyramids/Pyramids-2000026.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000029,
-            "file_path": "results/Pyramids Training6/Pyramids.onnx",
-            "reward": 1.704285700406347,
-            "creation_time": 1697030675.6403673,
+            "steps": 2000026,
+            "file_path": "results/Pyramids Training7/Pyramids.onnx",
+            "reward": 1.659699985384941,
+            "creation_time": 1697035811.7303658,
             "auxillary_file_paths": [
-                "results/Pyramids Training6/Pyramids/Pyramids-1000029.pt"
+                "results/Pyramids Training7/Pyramids/Pyramids-2000026.pt"
             ]
         }
     },