First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fde8ffbbcad3c8944fd28a9d33ee206ebba9a053e244205b7e45fa4eb6a66f8
+oid sha256:ad342fd11521eeda2d4742d92249336f2aebd6321a3488e2cf68703f1f7f9e8c
 size 1420238

Pyramids/Pyramids-1499952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562305908af21e9fc57ff7f75e352d37e13256975bedbdcf1b454258b329d0ae
+size 1420238

Pyramids/Pyramids-1499952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f128040abfe05ba209652f2a7a9252c434a991778464f7a8696735f03d8d58
+size 8656731

Pyramids/Pyramids-1800022.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad342fd11521eeda2d4742d92249336f2aebd6321a3488e2cf68703f1f7f9e8c
+size 1420238

Pyramids/Pyramids-1800022.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e372558ebeed514e7254b5614fb2c5b70507fff6f2f73b6973568226964f0f0
+size 8656731

Pyramids/Pyramids-499936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7555daa3deaa9208398ee6655a8d26ce33556e65d83e5ef72fa6f1e1c8bca769
+size 1420238

Pyramids/Pyramids-499936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:491047ede48e965dd1818d9b0f341a23b111b07687c28a0c95e3d94cded5d81c
+size 8656650

Pyramids/Pyramids-999978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7db5e0eaa6565693b01e5e34bf85661c0456c7e3f91d47b7c7fa016f2609ae
+size 1420238

Pyramids/Pyramids-999978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca0282054fea3de12c2d0fa8eeb32961ea57b9021cee89480d3cb34af78af1a
+size 8656650

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8168664f116066b7c32b3b3d3eaef1ec63abbd8ca689bb67804bf5f16dc8b31
+oid sha256:cac8c38da0712ec23c39ebf28de00ea2dddecf2de747a46ced3a06f827305b41
 size 8656181

Pyramids/events.out.tfevents.1754687081.abe68d5c0ce0.21223.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872aeb9f05be6aa369453361f176c09bb291896f10880849e304e3ee4c6e9b74
+size 584883

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1800000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training2", "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

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 1800000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -79,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training1
+  run_id: Pyramids Training2
   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] 55119 [Flags] 2 [Guid] 3528729794 [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] 55183 [Flags] 2 [Guid] 809316105 [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  0.090 seconds
+- Completed reload, in  0.087 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: 1.047294 ms
+UnloadTime: 0.828187 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]: 5894 frames, [32.0 KB-64.0 KB]: 9974 frames, [64.0 KB-128.0 KB]: 2896 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 5598 frames, [32.0 KB-64.0 KB]: 19964 frames, [64.0 KB-128.0 KB]: 8203 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
@@ -123,17 +123,17 @@ 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
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       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 2]
+    [ALLOC_TEMP_Background Job.Worker 7]
       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]: 18466 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 33467 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.5 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12270
+  Peak main deferred allocation count 12348
     [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]: 18764 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 33765 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.8 MB
+      Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18765 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 33766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.9 MB
+      Peak Allocated memory 22.6 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]: 18764 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 33765 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]: 18765 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 33766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,13 +272,13 @@ 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]: 18466 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 33467 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]: 18764 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 33765 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
@@ -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]: 18765 frames
+      Peak usage frame count: [0-1.0 KB]: 33766 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]: 18765 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 33766 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]: 18765 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 33766 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 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":1754686564117,"processId":9942,"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":1754691251057,"processId":21243,"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": 0.45451077818870544,
-            "min": 0.45451077818870544,
-            "max": 1.46808660030365,
-            "count": 33
+            "value": 0.1860702782869339,
+            "min": 0.1860702782869339,
+            "max": 1.359559178352356,
+            "count": 60
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 13613.5068359375,
-            "min": 13510.71875,
-            "max": 44535.875,
-            "count": 33
+            "value": 5596.994140625,
+            "min": 5596.994140625,
+            "max": 41243.5859375,
+            "count": 60
         },
         "Pyramids.Step.mean": {
-            "value": 989907.0,
-            "min": 29952.0,
-            "max": 989907.0,
-            "count": 33
+            "value": 1799894.0,
+            "min": 29994.0,
+            "max": 1799894.0,
+            "count": 60
         },
         "Pyramids.Step.sum": {
-            "value": 989907.0,
-            "min": 29952.0,
-            "max": 989907.0,
-            "count": 33
+            "value": 1799894.0,
+            "min": 29994.0,
+            "max": 1799894.0,
+            "count": 60
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.552248477935791,
-            "min": -0.12838654220104218,
-            "max": 0.586003839969635,
-            "count": 33
+            "value": 0.750239908695221,
+            "min": -0.12088796496391296,
+            "max": 0.814854621887207,
+            "count": 60
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 154.62957763671875,
-            "min": -30.638519287109375,
-            "max": 162.32305908203125,
-            "count": 33
+            "value": 222.82125854492188,
+            "min": -29.13399887084961,
+            "max": 243.64154052734375,
+            "count": 60
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.004538350272923708,
-            "min": -0.008090514689683914,
-            "max": 0.45865797996520996,
-            "count": 33
+            "value": 0.014512973837554455,
+            "min": -0.0027909132186323404,
+            "max": 0.3900887072086334,
+            "count": 60
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.270738124847412,
-            "min": -2.1763484477996826,
-            "max": 108.70194244384766,
-            "count": 33
+            "value": 4.3103532791137695,
+            "min": -0.7256374359130859,
+            "max": 93.231201171875,
+            "count": 60
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06949576318757386,
-            "min": 0.06595955327939777,
-            "max": 0.07419247324055085,
-            "count": 33
+            "value": 0.06815001877366841,
+            "min": 0.06392532331353454,
+            "max": 0.07420536054393502,
+            "count": 60
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9729406846260341,
-            "min": 0.49511408272544566,
-            "max": 1.067080382509933,
-            "count": 33
+            "value": 0.9541002628313578,
+            "min": 0.6321973723799953,
+            "max": 1.0687040154395313,
+            "count": 60
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.015920486102674377,
-            "min": 0.0011569716331876704,
-            "max": 0.01662300402157208,
-            "count": 33
+            "value": 0.01417358278923639,
+            "min": 0.0006356363043529755,
+            "max": 0.01871261339554275,
+            "count": 60
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.2228868054374413,
-            "min": 0.013883659598252045,
-            "max": 0.23272205630200915,
-            "count": 33
+            "value": 0.19843015904930947,
+            "min": 0.008263271956588682,
+            "max": 0.2619765875375985,
+            "count": 60
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.441147519649999e-06,
-            "min": 7.441147519649999e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 2.3358968404484103e-06,
+            "min": 2.3358968404484103e-06,
+            "max": 0.00029711603799835803,
+            "count": 60
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010417606527509998,
-            "min": 0.00010417606527509998,
-            "max": 0.003509697230101,
-            "count": 33
+            "value": 3.2702555766277745e-05,
+            "min": 3.2702555766277745e-05,
+            "max": 0.0036751453416182774,
+            "count": 60
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10248035000000001,
-            "min": 0.10248035000000001,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10077859920634923,
+            "min": 0.10077859920634923,
+            "max": 0.1990386790123457,
+            "count": 60
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4347249000000002,
-            "min": 1.3886848,
-            "max": 2.5698990000000004,
-            "count": 33
+            "value": 1.4109003888888891,
+            "min": 1.4109003888888891,
+            "max": 2.6875465555555555,
+            "count": 60
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002577869649999999,
-            "min": 0.0002577869649999999,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 8.778206071428562e-05,
+            "min": 8.778206071428562e-05,
+            "max": 0.009903964033333332,
+            "count": 60
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.003609017509999999,
-            "min": 0.003609017509999999,
-            "max": 0.1170129101,
-            "count": 33
+            "value": 0.0012289488499999987,
+            "min": 0.0012289488499999987,
+            "max": 0.12252233405,
+            "count": 60
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.009625582955777645,
-            "min": 0.009625582955777645,
-            "max": 0.5081137418746948,
-            "count": 33
+            "value": 0.009783700108528137,
+            "min": 0.009783700108528137,
+            "max": 0.5258215069770813,
+            "count": 60
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.13475815951824188,
-            "min": 0.13475815951824188,
-            "max": 3.556796073913574,
-            "count": 33
+            "value": 0.13697180151939392,
+            "min": 0.13697180151939392,
+            "max": 4.732393741607666,
+            "count": 60
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 344.1304347826087,
-            "min": 333.27906976744185,
-            "max": 999.0,
-            "count": 33
+            "value": 246.10084033613447,
+            "min": 224.6962962962963,
+            "max": 988.5,
+            "count": 60
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31660.0,
-            "min": 15984.0,
-            "max": 33661.0,
-            "count": 33
+            "value": 29286.0,
+            "min": 16792.0,
+            "max": 33884.0,
+            "count": 60
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.613929016856096,
-            "min": -1.0000000521540642,
-            "max": 1.6416202018435082,
-            "count": 33
+            "value": 1.720277294140904,
+            "min": -0.9269500519149005,
+            "max": 1.7753036922878689,
+            "count": 60
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 150.09539856761694,
-            "min": -28.944201588630676,
-            "max": 150.09539856761694,
-            "count": 33
+            "value": 204.71299800276756,
+            "min": -30.30800160765648,
+            "max": 239.6659984588623,
+            "count": 60
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.613929016856096,
-            "min": -1.0000000521540642,
-            "max": 1.6416202018435082,
-            "count": 33
+            "value": 1.720277294140904,
+            "min": -0.9269500519149005,
+            "max": 1.7753036922878689,
+            "count": 60
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 150.09539856761694,
-            "min": -28.944201588630676,
-            "max": 150.09539856761694,
-            "count": 33
+            "value": 204.71299800276756,
+            "min": -30.30800160765648,
+            "max": 239.6659984588623,
+            "count": 60
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.03411730383153534,
-            "min": 0.03411730383153534,
-            "max": 10.79082521237433,
-            "count": 33
+            "value": 0.02504550329102421,
+            "min": 0.023912899854167335,
+            "max": 9.307265160812271,
+            "count": 60
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.1729092563327868,
-            "min": 3.070275793565088,
-            "max": 172.65320339798927,
-            "count": 33
+            "value": 2.980414891631881,
+            "min": 2.980414891631881,
+            "max": 167.5307728946209,
+            "count": 60
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 60
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 60
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1754684430",
+        "start_time_seconds": "1754687081",
         "python_version": "3.10.12 (main, May 27 2025, 17:12:29) [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 Training1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1754686564"
+        "end_time_seconds": "1754691251"
     },
-    "total": 2133.2706661639995,
+    "total": 4169.988305986,
     "count": 1,
-    "self": 0.4762967389988262,
+    "self": 0.9705933849991197,
     "children": {
         "run_training.setup": {
-            "total": 0.020550393000121403,
+            "total": 0.02064092500040715,
             "count": 1,
-            "self": 0.020550393000121403
+            "self": 0.02064092500040715
         },
         "TrainerController.start_learning": {
-            "total": 2132.7738190320006,
+            "total": 4168.997071676001,
             "count": 1,
-            "self": 1.25130392402707,
+            "self": 2.3067529021127484,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.8119471240001985,
+                    "total": 2.474826863999624,
                     "count": 1,
-                    "self": 2.8119471240001985
+                    "self": 2.474826863999624
                 },
                 "TrainerController.advance": {
-                    "total": 2128.6335253209736,
-                    "count": 63856,
-                    "self": 1.2777586849933869,
+                    "total": 4164.105640571888,
+                    "count": 116292,
+                    "self": 2.3381395673986844,
                     "children": {
                         "env_step": {
-                            "total": 1484.29750513803,
-                            "count": 63856,
-                            "self": 1343.8633470159166,
+                            "total": 2981.550744245009,
+                            "count": 116292,
+                            "self": 2732.3633181293017,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 139.68422313105475,
-                                    "count": 63856,
-                                    "self": 4.457120087014573,
+                                    "total": 247.838306047689,
+                                    "count": 116292,
+                                    "self": 7.897070007629736,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 135.22710304404018,
-                                            "count": 62548,
-                                            "self": 135.22710304404018
+                                            "total": 239.94123604005927,
+                                            "count": 112553,
+                                            "self": 239.94123604005927
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7499349910585806,
-                                    "count": 63856,
+                                    "total": 1.3491200680182374,
+                                    "count": 116292,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2128.5424326140023,
-                                            "count": 63856,
+                                            "total": 4160.567250168144,
+                                            "count": 116292,
                                             "is_parallel": true,
-                                            "self": 890.7317522809622,
+                                            "self": 1623.080052718149,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0024449950001326215,
+                                                            "total": 0.0019109590002699406,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006890259996907844,
+                                                            "self": 0.0006274510005823686,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0017559690004418371,
+                                                                    "total": 0.001283507999687572,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0017559690004418371
+                                                                    "self": 0.001283507999687572
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.048762222999812366,
+                                                            "total": 0.08311142000002292,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005220449997977994,
+                                                            "self": 0.0005440510003609234,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004723920001197257,
+                                                                    "total": 0.0004223890000503161,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004723920001197257
+                                                                    "self": 0.0004223890000503161
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04614995200017802,
+                                                                    "total": 0.0806384010002148,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04614995200017802
+                                                                    "self": 0.0806384010002148
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016178339997168223,
+                                                                    "total": 0.0015065789993968792,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000337593000040215,
+                                                                    "self": 0.0003091590006079059,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012802409996766073,
+                                                                            "total": 0.0011974199987889733,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012802409996766073
+                                                                            "self": 0.0011974199987889733
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1237.8106803330402,
-                                                    "count": 63855,
+                                                    "total": 2537.4871974499947,
+                                                    "count": 116291,
                                                     "is_parallel": true,
-                                                    "self": 31.300092845992822,
+                                                    "self": 56.65517621392519,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 21.727901769032087,
-                                                            "count": 63855,
+                                                            "total": 39.24100072593046,
+                                                            "count": 116291,
                                                             "is_parallel": true,
-                                                            "self": 21.727901769032087
+                                                            "self": 39.24100072593046
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1091.1582201609726,
-                                                            "count": 63855,
+                                                            "total": 2270.6421179820845,
+                                                            "count": 116291,
                                                             "is_parallel": true,
-                                                            "self": 1091.1582201609726
+                                                            "self": 2270.6421179820845
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 93.62446555704264,
-                                                            "count": 63855,
+                                                            "total": 170.94890252805453,
+                                                            "count": 116291,
                                                             "is_parallel": true,
-                                                            "self": 18.332959460876282,
+                                                            "self": 34.179239453719674,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 75.29150609616636,
-                                                                    "count": 510840,
+                                                                    "total": 136.76966307433486,
+                                                                    "count": 930328,
                                                                     "is_parallel": true,
-                                                                    "self": 75.29150609616636
+                                                                    "self": 136.76966307433486
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 643.0582614979503,
-                            "count": 63856,
-                            "self": 2.441878296934192,
+                            "total": 1180.2167567594806,
+                            "count": 116292,
+                            "self": 4.635326441661164,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 120.8793044150193,
-                                    "count": 63856,
-                                    "self": 120.63395444901926,
+                                    "total": 228.41005177381976,
+                                    "count": 116292,
+                                    "self": 228.07657607082092,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.24534996600004888,
-                                            "count": 2,
-                                            "self": 0.24534996600004888
+                                            "total": 0.33347570299883955,
+                                            "count": 3,
+                                            "self": 0.33347570299883955
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 519.7370787859968,
-                                    "count": 452,
-                                    "self": 290.0723896809659,
+                                    "total": 947.1713785439997,
+                                    "count": 834,
+                                    "self": 529.0756864350451,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 229.6646891050309,
-                                            "count": 22803,
-                                            "self": 229.6646891050309
+                                            "total": 418.0956921089546,
+                                            "count": 41022,
+                                            "self": 418.0956921089546
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.53000528877601e-07,
+                    "total": 1.2870004866272211e-06,
                     "count": 1,
-                    "self": 8.53000528877601e-07
+                    "self": 1.2870004866272211e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07704180999917298,
+                    "total": 0.10985005099973932,
                     "count": 1,
-                    "self": 0.0012942789990120218,
+                    "self": 0.0021647129997290904,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.07574753100016096,
+                            "total": 0.10768533800001023,
                             "count": 1,
-                            "self": 0.07574753100016096
+                            "self": 0.10768533800001023
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,49 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499918,
-                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-499918.onnx",
-                "reward": null,
-                "creation_time": 1754685424.0982752,
+                "steps": 499936,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-499936.onnx",
+                "reward": -0.4052500482648611,
+                "creation_time": 1754688046.290308,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training1/Pyramids/Pyramids-499918.pt"
+                    "results/Pyramids Training2/Pyramids/Pyramids-499936.pt"
                 ]
             },
             {
-                "steps": 999907,
-                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-999907.onnx",
+                "steps": 999978,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-999978.onnx",
                 "reward": null,
-                "creation_time": 1754686563.5958457,
+                "creation_time": 1754689235.6184068,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training1/Pyramids/Pyramids-999907.pt"
+                    "results/Pyramids Training2/Pyramids/Pyramids-999978.pt"
                 ]
             },
             {
-                "steps": 1000035,
-                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-1000035.onnx",
-                "reward": null,
-                "creation_time": 1754686563.6835418,
+                "steps": 1499952,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-1499952.onnx",
+                "reward": 1.7470000013709068,
+                "creation_time": 1754690482.7895226,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training2/Pyramids/Pyramids-1499952.pt"
+                ]
+            },
+            {
+                "steps": 1800022,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-1800022.onnx",
+                "reward": 1.8529999405145645,
+                "creation_time": 1754691250.1571503,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training1/Pyramids/Pyramids-1000035.pt"
+                    "results/Pyramids Training2/Pyramids/Pyramids-1800022.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000035,
-            "file_path": "results/Pyramids Training1/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1754686563.6835418,
+            "steps": 1800022,
+            "file_path": "results/Pyramids Training2/Pyramids.onnx",
+            "reward": 1.8529999405145645,
+            "creation_time": 1754691250.1571503,
             "auxillary_file_paths": [
-                "results/Pyramids Training1/Pyramids/Pyramids-1000035.pt"
+                "results/Pyramids Training2/Pyramids/Pyramids-1800022.pt"
             ]
         }
     },