Learning Rate 0.0001

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab3a5b9fe6e4e27fbce3cd1e68925c165e44b4ab0e94f514ff50acfe95e6bbc9
+oid sha256:991cc8f56c338d1776c10b44ffe3f3c48a5ee972ea870582dc0b53ca80a1a3bb
 size 1420238

Pyramids/Pyramids-1000129.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991cc8f56c338d1776c10b44ffe3f3c48a5ee972ea870582dc0b53ca80a1a3bb
+size 1420238

Pyramids/Pyramids-1000129.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a6676f682fd89871937326c0d8fea72fb0b02c7db34e69b106b0f784633235
+size 8656252

Pyramids/Pyramids-499857.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7569556a5b7e727fac83bf234669bf138e13ae84bd97a00c567161adfee7e2
+size 1420238

Pyramids/Pyramids-499857.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aab7d835419a0ebbf0e00c142b0eca0ee63b83c40d22164b97f1db98d96747a
+size 8656173

Pyramids/Pyramids-999873.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991cc8f56c338d1776c10b44ffe3f3c48a5ee972ea870582dc0b53ca80a1a3bb
+size 1420238

Pyramids/Pyramids-999873.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ae9a8fcbbfb8c2adfd7c81186d437f6a9053f66d3a0e4bf4896591e342d602
+size 8656173

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a4eed4dd055f7d3279263ddb00207718899dd81179075c81e89798decc579e
+oid sha256:176cc6a8bd400c6c938a7e94166f0a7fecd26a0e1b486a78f046e5094aecce4a
 size 8655778

Pyramids/events.out.tfevents.1716437138.94659798b8d5.32492.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc36bb4ff12eb43ed28caa7bb6b3412d877357ea882ef1769b9cd3629de1753f
+size 824933

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": 256, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training 1", "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": 0.0001, "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": 256, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training 2", "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

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0003
+      learning_rate: 0.0001
       beta: 0.01
       epsilon: 0.2
       lambd: 0.95
@@ -79,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training 1
+  run_id: Pyramids Training 2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/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] 55479 [Flags] 2 [Guid] 3458033735 [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] 55160 [Flags] 2 [Guid] 1900115762 [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  0.091 seconds
+- Completed reload, in  0.136 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: 1.131369 ms
+UnloadTime: 0.928096 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]: 3577 frames, [32.0 KB-64.0 KB]: 11714 frames, [64.0 KB-128.0 KB]: 3486 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 7120 frames, [32.0 KB-64.0 KB]: 9989 frames, [64.0 KB-128.0 KB]: 1674 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
@@ -93,11 +93,6 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AUDIO_FMOD mixer thread]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 1]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -146,7 +141,7 @@ 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 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -173,6 +168,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_AUDIO_Audio Mixer Thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -204,29 +204,29 @@ 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]: 18479 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18485 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 11956
+  Peak main deferred allocation count 12613
     [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]: 18777 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 18783 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.7 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 46.2 MB
+      Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18778 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 18783 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.7 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 8.0 MB
+      Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -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]: 18777 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18783 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]: 18778 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18784 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]: 18479 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18485 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]: 18777 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18783 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
+      Peak Allocated memory 4.1 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -290,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18778 frames
+      Peak usage frame count: [0-1.0 KB]: 18784 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]: 18778 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18784 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]: 18778 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18784 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -311,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1716436883241,"processId":21638,"allocatedMemory":1970103,"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":3417},{"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":1716439267130,"processId":32527,"allocatedMemory":1970104,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10604},{"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":3417},{"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

@@ -2,123 +2,123 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.3481403589248657,
-            "min": 0.3219470679759979,
-            "max": 1.5952553749084473,
+            "value": 0.8850176334381104,
+            "min": 0.8331785202026367,
+            "max": 1.5876655578613281,
             "count": 100
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 3392.279541015625,
-            "min": 3229.9716796875,
-            "max": 19602.498046875,
+            "value": 8482.0087890625,
+            "min": 7631.3837890625,
+            "max": 19509.234375,
             "count": 100
         },
         "Pyramids.Step.mean": {
-            "value": 999928.0,
+            "value": 999873.0,
             "min": 9984.0,
-            "max": 999928.0,
+            "max": 999873.0,
             "count": 100
         },
         "Pyramids.Step.sum": {
-            "value": 999928.0,
+            "value": 999873.0,
             "min": 9984.0,
-            "max": 999928.0,
+            "max": 999873.0,
             "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.6715216040611267,
-            "min": -0.11322605609893799,
-            "max": 0.7164641618728638,
+            "value": 0.11677168309688568,
+            "min": -0.1126600131392479,
+            "max": 0.26561713218688965,
             "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 38.9482536315918,
-            "min": -4.5290422439575195,
-            "max": 40.12199401855469,
+            "value": 4.787639141082764,
+            "min": -4.731720447540283,
+            "max": 12.484004974365234,
             "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.10299792885780334,
-            "min": -0.10299792885780334,
-            "max": 0.43480196595191956,
+            "value": -0.010345344431698322,
+            "min": -0.03231552243232727,
+            "max": 0.4831255078315735,
             "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -5.973879814147949,
-            "min": -5.973879814147949,
-            "max": 17.392078399658203,
+            "value": -0.42415910959243774,
+            "min": -1.518829584121704,
+            "max": 19.32501983642578,
             "count": 100
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06717844910956189,
-            "min": 0.06162684253535653,
-            "max": 0.07925617498403881,
+            "value": 0.06923260019462117,
+            "min": 0.060321219902544146,
+            "max": 0.08108076048836879,
             "count": 100
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.33589224554780944,
-            "min": 0.12955030049973476,
-            "max": 0.38342814044981244,
+            "value": 0.34616300097310587,
+            "min": 0.12064243980508829,
+            "max": 0.3794934761998079,
             "count": 100
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01792239473434165,
-            "min": 0.0003642205551083558,
-            "max": 0.01889296545414254,
+            "value": 0.008926889326539822,
+            "min": 0.0001672080627686915,
+            "max": 0.0195200189773459,
             "count": 100
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.08961197367170826,
-            "min": 0.0007284411102167117,
-            "max": 0.08961197367170826,
+            "value": 0.04463444663269911,
+            "min": 0.00037139437674162817,
+            "max": 0.06197965337428385,
             "count": 100
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 1.3214195595599926e-06,
-            "min": 1.3214195595599926e-06,
-            "max": 0.0002981568006144,
+            "value": 5.203994797000002e-07,
+            "min": 5.203994797000002e-07,
+            "max": 9.938560061440002e-05,
             "count": 100
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 6.607097797799963e-06,
-            "min": 6.607097797799963e-06,
-            "max": 0.0011325766224745,
+            "value": 2.6019973985000013e-06,
+            "min": 2.6019973985000013e-06,
+            "max": 0.0003524194475807,
             "count": 100
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10044043999999999,
-            "min": 0.10044043999999999,
+            "value": 0.10052029999999998,
+            "min": 0.10052029999999998,
             "max": 0.1993856,
             "count": 100
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 0.5022021999999999,
-            "min": 0.3629047000000001,
-            "max": 0.8775255,
+            "value": 0.5026014999999999,
+            "min": 0.33905510000000005,
+            "max": 0.8524193,
             "count": 100
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 5.3999955999999754e-05,
-            "min": 5.3999955999999754e-05,
+            "value": 6.197797000000002e-05,
+            "min": 6.197797000000002e-05,
             "max": 0.00993862144,
             "count": 100
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.00026999977999999877,
-            "min": 0.00026999977999999877,
-            "max": 0.037764797450000005,
+            "value": 0.0003098898500000001,
+            "min": 0.0003098898500000001,
+            "max": 0.03525668807,
             "count": 100
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.013221800327301025,
-            "min": 0.013021955266594887,
-            "max": 1.007627248764038,
+            "value": 0.016881264746189117,
+            "min": 0.015998484566807747,
+            "max": 0.6382833123207092,
             "count": 100
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.06610900163650513,
-            "min": 0.05300857499241829,
-            "max": 2.015254497528076,
+            "value": 0.08440632373094559,
+            "min": 0.06399393826723099,
+            "max": 1.2765666246414185,
             "count": 100
         },
         "Pyramids.IsTraining.mean": {
@@ -134,117 +134,117 @@
             "count": 100
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 265.4047619047619,
-            "min": 260.25,
+            "value": 784.9090909090909,
+            "min": 549.8666666666667,
             "max": 999.0,
-            "count": 98
+            "count": 96
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 11147.0,
-            "min": 1760.0,
+            "value": 8634.0,
+            "min": 999.0,
             "max": 15984.0,
-            "count": 98
+            "count": 96
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6843853432957718,
+            "value": 0.48752723227847705,
             "min": -1.0000000596046448,
-            "max": 1.7418107962286151,
-            "count": 99
+            "max": 0.9166132907072703,
+            "count": 97
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 69.05979907512665,
+            "value": 5.362799555063248,
             "min": -16.000000953674316,
-            "max": 69.05979907512665,
-            "count": 99
+            "max": 13.901399582624435,
+            "count": 97
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6843853432957718,
+            "value": 0.48752723227847705,
             "min": -1.0000000596046448,
-            "max": 1.7418107962286151,
-            "count": 99
+            "max": 0.9166132907072703,
+            "count": 97
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 69.05979907512665,
+            "value": 5.362799555063248,
             "min": -16.000000953674316,
-            "max": 69.05979907512665,
-            "count": 99
+            "max": 13.901399582624435,
+            "count": 97
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.03648825318597984,
-            "min": 0.03648825318597984,
-            "max": 9.871843811124563,
-            "count": 99
+            "value": 0.12992440299554306,
+            "min": 0.09765435053656499,
+            "max": 7.740425918251276,
+            "count": 97
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 1.4960183806251734,
-            "min": 1.1329713931772858,
-            "max": 157.949500977993,
-            "count": 99
+            "value": 1.4291684329509735,
+            "min": 1.200802855193615,
+            "max": 123.84681469202042,
+            "count": 97
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1716434592",
+        "start_time_seconds": "1716437137",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/MyPyramid.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/MyPyramid.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 2 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1716436883"
+        "end_time_seconds": "1716439267"
     },
-    "total": 2290.3266880849997,
+    "total": 2130.1321710069997,
     "count": 1,
-    "self": 0.4771557589992881,
+    "self": 0.47590122899873677,
     "children": {
         "run_training.setup": {
-            "total": 0.07051015100023506,
+            "total": 0.061227402000440634,
             "count": 1,
-            "self": 0.07051015100023506
+            "self": 0.061227402000440634
         },
         "TrainerController.start_learning": {
-            "total": 2289.779022175,
+            "total": 2129.5950423760005,
             "count": 1,
-            "self": 1.4342343309599528,
+            "self": 1.3536567451064911,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.26019578299929,
+                    "total": 3.303271632999895,
                     "count": 1,
-                    "self": 2.26019578299929
+                    "self": 3.303271632999895
                 },
                 "TrainerController.advance": {
-                    "total": 2286.0000442570417,
-                    "count": 64081,
-                    "self": 1.4486732639625188,
+                    "total": 2124.8491485318937,
+                    "count": 63337,
+                    "self": 1.4641935372037551,
                     "children": {
                         "env_step": {
-                            "total": 1648.9823435820135,
-                            "count": 64081,
-                            "self": 1508.3017766729217,
+                            "total": 1498.4707922458356,
+                            "count": 63337,
+                            "self": 1357.2551201791512,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 139.79050587699203,
-                                    "count": 64081,
-                                    "self": 4.960329730100966,
+                                    "total": 140.36581647694584,
+                                    "count": 63337,
+                                    "self": 4.948217196894802,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 134.83017614689106,
-                                            "count": 62593,
-                                            "self": 134.83017614689106
+                                            "total": 135.41759928005104,
+                                            "count": 62613,
+                                            "self": 135.41759928005104
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8900610320997657,
-                                    "count": 64081,
+                                    "total": 0.8498555897385813,
+                                    "count": 63337,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2284.071174495808,
-                                            "count": 64081,
+                                            "total": 2124.5911870220916,
+                                            "count": 63337,
                                             "is_parallel": true,
-                                            "self": 906.0645742377956,
+                                            "self": 896.1461144302948,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0020555150003929157,
+                                                            "total": 0.0030324310000651167,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000609143999099615,
+                                                            "self": 0.0007891719978943001,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014463710012933007,
+                                                                    "total": 0.0022432590021708165,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014463710012933007
+                                                                    "self": 0.0022432590021708165
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0529998540005181,
+                                                            "total": 0.07773992199963686,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006919500010553747,
+                                                            "self": 0.0006560700003319653,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00048651699944457505,
+                                                                    "total": 0.00048155300009966595,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00048651699944457505
+                                                                    "self": 0.00048155300009966595
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.049611530999754905,
+                                                                    "total": 0.07256154399965453,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.049611530999754905
+                                                                    "self": 0.07256154399965453
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002209856000263244,
+                                                                    "total": 0.0040407549995507,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00042540900085441535,
+                                                                    "self": 0.0024929090004661703,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0017844469994088286,
+                                                                            "total": 0.0015478459990845295,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0017844469994088286
+                                                                            "self": 0.0015478459990845295
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1378.0066002580124,
-                                                    "count": 64080,
+                                                    "total": 1228.4450725917968,
+                                                    "count": 63336,
                                                     "is_parallel": true,
-                                                    "self": 35.05879043918594,
+                                                    "self": 34.71951610774704,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 25.00306529098907,
-                                                            "count": 64080,
+                                                            "total": 25.543849263031916,
+                                                            "count": 63336,
                                                             "is_parallel": true,
-                                                            "self": 25.00306529098907
+                                                            "self": 25.543849263031916
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1213.3965179539446,
-                                                            "count": 64080,
+                                                            "total": 1063.5557917759343,
+                                                            "count": 63336,
                                                             "is_parallel": true,
-                                                            "self": 1213.3965179539446
+                                                            "self": 1063.5557917759343
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 104.54822657389286,
-                                                            "count": 64080,
+                                                            "total": 104.62591544508359,
+                                                            "count": 63336,
                                                             "is_parallel": true,
-                                                            "self": 21.68169286695047,
+                                                            "self": 21.089426738714792,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 82.86653370694239,
-                                                                    "count": 512640,
+                                                                    "total": 83.5364887063688,
+                                                                    "count": 506688,
                                                                     "is_parallel": true,
-                                                                    "self": 82.86653370694239
+                                                                    "self": 83.5364887063688
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 635.5690274110657,
-                            "count": 64081,
-                            "self": 2.789846189916716,
+                            "total": 624.9141627488543,
+                            "count": 63337,
+                            "self": 2.769332938797561,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 117.68227903414572,
-                                    "count": 64081,
-                                    "self": 117.48042283214545,
+                                    "total": 112.72656429404924,
+                                    "count": 63337,
+                                    "self": 112.52870114904908,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.20185620200027188,
+                                            "total": 0.19786314500015578,
                                             "count": 2,
-                                            "self": 0.20185620200027188
+                                            "self": 0.19786314500015578
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 515.0969021870033,
-                                    "count": 416,
-                                    "self": 304.39398667298883,
+                                    "total": 509.4182655160075,
+                                    "count": 393,
+                                    "self": 301.02186049410375,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 210.70291551401442,
-                                            "count": 22887,
-                                            "self": 210.70291551401442
+                                            "total": 208.39640502190377,
+                                            "count": 22878,
+                                            "self": 208.39640502190377
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.689994501764886e-07,
+                    "total": 1.0889998520724475e-06,
                     "count": 1,
-                    "self": 8.689994501764886e-07
+                    "self": 1.0889998520724475e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08454693499970745,
+                    "total": 0.08896437700059323,
                     "count": 1,
-                    "self": 0.0013945529990451178,
+                    "self": 0.0013606700013042428,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08315238200066233,
+                            "total": 0.08760370699928899,
                             "count": 1,
-                            "self": 0.08315238200066233
+                            "self": 0.08760370699928899
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499817,
-                "file_path": "results/Pyramids Training 1/Pyramids/Pyramids-499817.onnx",
-                "reward": 1.391499936580658,
-                "creation_time": 1716435623.5685778,
+                "steps": 499857,
+                "file_path": "results/Pyramids Training 2/Pyramids/Pyramids-499857.onnx",
+                "reward": null,
+                "creation_time": 1716438175.6800215,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training 1/Pyramids/Pyramids-499817.pt"
+                    "results/Pyramids Training 2/Pyramids/Pyramids-499857.pt"
                 ]
             },
             {
-                "steps": 999928,
-                "file_path": "results/Pyramids Training 1/Pyramids/Pyramids-999928.onnx",
-                "reward": 1.676000028848648,
-                "creation_time": 1716436882.7105162,
+                "steps": 999873,
+                "file_path": "results/Pyramids Training 2/Pyramids/Pyramids-999873.onnx",
+                "reward": -0.999800056219101,
+                "creation_time": 1716439266.5738575,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training 1/Pyramids/Pyramids-999928.pt"
+                    "results/Pyramids Training 2/Pyramids/Pyramids-999873.pt"
                 ]
             },
             {
-                "steps": 1000136,
-                "file_path": "results/Pyramids Training 1/Pyramids/Pyramids-1000136.onnx",
-                "reward": 1.7345000058412552,
-                "creation_time": 1716436882.8116915,
+                "steps": 1000129,
+                "file_path": "results/Pyramids Training 2/Pyramids/Pyramids-1000129.onnx",
+                "reward": -0.999800056219101,
+                "creation_time": 1716439266.683803,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training 1/Pyramids/Pyramids-1000136.pt"
+                    "results/Pyramids Training 2/Pyramids/Pyramids-1000129.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000136,
-            "file_path": "results/Pyramids Training 1/Pyramids.onnx",
-            "reward": 1.7345000058412552,
-            "creation_time": 1716436882.8116915,
+            "steps": 1000129,
+            "file_path": "results/Pyramids Training 2/Pyramids.onnx",
+            "reward": -0.999800056219101,
+            "creation_time": 1716439266.683803,
             "auxillary_file_paths": [
-                "results/Pyramids Training 1/Pyramids/Pyramids-1000136.pt"
+                "results/Pyramids Training 2/Pyramids/Pyramids-1000129.pt"
             ]
         }
     },