First try

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91784c2889436c9e7e4cc3a537f6fea38960e27b285a243a2f594558b2495a08
+oid sha256:3e39a4d41d8286f26c7a304d8ecf0d41ac68b16524e186ca8b9941d0668e772c
 size 1420238

Pyramids/Pyramids-1999957.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5542527f5a2c370ff0a2e2755ee681b8d0acc531d6efa46bb1edfaf104c96b08
+size 1420238

Pyramids/Pyramids-1999957.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e6e68e20216f68b5f910538a87fd8ccebe10c7c301f12670dbfad47c216f57
+size 8656252

Pyramids/Pyramids-2499814.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9a3932f85e72e657654f2fa9bac2875e64734d50449464f0f1078cfb1c5baa
+size 1420238

Pyramids/Pyramids-2499814.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff10e81e9dc0ed4fa169ccdcc5d63b3965554596da29d2bc4775c61f022566e
+size 8656252

Pyramids/Pyramids-2785932.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abd9e9d35d36d857bffb860fcc90b185c61035235735e386d15a77120a0f0bb
+size 1420238

Pyramids/Pyramids-2785932.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13f8b01fd3c89c16a620a12ef2b657129054511c5a072e7ef5b8e8dcb006aeb
+size 8656252

Pyramids/Pyramids-2999867.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e39a4d41d8286f26c7a304d8ecf0d41ac68b16524e186ca8b9941d0668e772c
+size 1420238

Pyramids/Pyramids-2999867.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88bc960914dc529d3b2234b05cb5dd1bbb913b29877e8c09fb1e1f77e98ebc5d
+size 8656252

Pyramids/Pyramids-3000197.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e39a4d41d8286f26c7a304d8ecf0d41ac68b16524e186ca8b9941d0668e772c
+size 1420238

Pyramids/Pyramids-3000197.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fa03eb39e7adddbd4868b5f9273ea1a96abc807cf219c2f71657896c218dd39
+size 8656252

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5d0ac53a124f61a5760458d6b9f461d3ca33e33807a9a4c0d2ac5734fb76f57
+oid sha256:8e37d9284f702a2050949cdf43dccd9b15e45b9b2eafa0945cd025a644635e5f
 size 8655778

Pyramids/events.out.tfevents.1736611229.395215bec3f4.28167.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e387622b6202380cbe04eda813754ec2454cc30102245480cdc62a6ff3a4ad
+size 389874

Pyramids/events.out.tfevents.1736614885.395215bec3f4.43658.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f9241f779f5af120a575c82ac6af1c6795f1a86b9125721b50d268c01e50b9
+size 65262

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 4096, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1500000, "time_horizon": 256, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 4096, "learning_rate": 0.0001, "beta": 0.001, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 512, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,10 +3,10 @@ behaviors:
   Pyramids:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
+      batch_size: 256
       buffer_size: 4096
-      learning_rate: 0.0003
-      beta: 0.01
+      learning_rate: 0.0001
+      beta: 0.001
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -51,8 +51,8 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1500000
-    time_horizon: 256
+    max_steps: 3000000
+    time_horizon: 512
     summary_freq: 30000
     threaded: false
     self_play: null

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] 55255 [Flags] 2 [Guid] 3222168327 [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] 55152 [Flags] 2 [Guid] 2844090387 [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  0.089 seconds
+- Completed reload, in  0.095 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.816895 ms
+UnloadTime: 0.850705 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]: 4233 frames, [32.0 KB-64.0 KB]: 2457 frames, [64.0 KB-128.0 KB]: 2722 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1262 frames, [32.0 KB-64.0 KB]: 1430 frames, [64.0 KB-128.0 KB]: 1368 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
@@ -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]: 44 frames, [1.0 MB-2.0 MB]: 9369 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 37 frames, [1.0 MB-2.0 MB]: 4024 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11553
+  Peak main deferred allocation count 5246
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.3 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9412 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 4060 frames
       Requested Block Size 16.0 MB
       Peak Block count 2
-      Peak Allocated memory 23.0 MB
+      Peak Allocated memory 23.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9413 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 4061 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.4 MB
+      Peak Allocated memory 22.0 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 1.3 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9412 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4060 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]: 9413 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 4061 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 1.3 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 55 frames, [1.0 MB-2.0 MB]: 9358 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 31 frames, [1.0 MB-2.0 MB]: 4030 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]: 9412 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 4060 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 1.3 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9413 frames
+      Peak usage frame count: [0-1.0 KB]: 4061 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]: 9413 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 4061 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]: 9413 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 4061 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 27.4 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":1736609298821,"processId":14551,"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":1736615475691,"processId":43698,"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}]}

run_logs/timers.json

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.34741145372390747,
-            "min": 0.33056017756462097,
-            "max": 0.4703061878681183,
-            "count": 17
+            "value": 0.19634008407592773,
+            "min": 0.18254616856575012,
+            "max": 0.20913568139076233,
+            "count": 8
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 10472.37109375,
-            "min": 9949.3662109375,
-            "max": 13494.453125,
-            "count": 17
+            "value": 6015.8603515625,
+            "min": 1244.887939453125,
+            "max": 6404.5712890625,
+            "count": 8
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 303.0576923076923,
-            "min": 273.70093457943926,
-            "max": 337.25274725274727,
-            "count": 17
+            "value": 227.02307692307693,
+            "min": 156.0,
+            "max": 274.3669724770642,
+            "count": 8
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31518.0,
-            "min": 18622.0,
-            "max": 32009.0,
-            "count": 17
+            "value": 29513.0,
+            "min": 4056.0,
+            "max": 30708.0,
+            "count": 8
         },
         "Pyramids.Step.mean": {
-            "value": 1499976.0,
-            "min": 1019772.0,
-            "max": 1499976.0,
-            "count": 17
+            "value": 2999867.0,
+            "min": 2789758.0,
+            "max": 2999867.0,
+            "count": 8
         },
         "Pyramids.Step.sum": {
-            "value": 1499976.0,
-            "min": 1019772.0,
-            "max": 1499976.0,
-            "count": 17
+            "value": 2999867.0,
+            "min": 2789758.0,
+            "max": 2999867.0,
+            "count": 8
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.6206983327865601,
-            "min": 0.5327100157737732,
-            "max": 0.6721581816673279,
-            "count": 17
+            "value": 0.6668941378593445,
+            "min": 0.5666171908378601,
+            "max": 0.6668941378593445,
+            "count": 8
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 102.41522216796875,
-            "min": 59.293670654296875,
-            "max": 112.25041961669922,
-            "count": 17
+            "value": 90.69760131835938,
+            "min": 14.709369659423828,
+            "max": 90.69760131835938,
+            "count": 8
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.014552807435393333,
-            "min": -0.0237854216247797,
-            "max": 0.024689558893442154,
-            "count": 17
+            "value": 0.007446997333317995,
+            "min": -0.0014452653704211116,
+            "max": 0.013798771426081657,
+            "count": 8
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 2.4012131690979004,
-            "min": -2.4736838340759277,
-            "max": 4.0490875244140625,
-            "count": 17
+            "value": 1.012791633605957,
+            "min": -0.17054131627082825,
+            "max": 1.6834501028060913,
+            "count": 8
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6195634368520517,
-            "min": 1.5553738957513934,
-            "max": 1.709380929242997,
-            "count": 17
+            "value": 1.773646126802151,
+            "min": 1.6794156214465266,
+            "max": 1.847959976196289,
+            "count": 8
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 168.43459743261337,
-            "min": 96.37499889731407,
-            "max": 179.48499757051468,
-            "count": 17
+            "value": 230.57399648427963,
+            "min": 46.19899940490723,
+            "max": 230.57399648427963,
+            "count": 8
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6195634368520517,
-            "min": 1.5553738957513934,
-            "max": 1.709380929242997,
-            "count": 17
+            "value": 1.773646126802151,
+            "min": 1.6794156214465266,
+            "max": 1.847959976196289,
+            "count": 8
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 168.43459743261337,
-            "min": 96.37499889731407,
-            "max": 179.48499757051468,
-            "count": 17
+            "value": 230.57399648427963,
+            "min": 46.19899940490723,
+            "max": 230.57399648427963,
+            "count": 8
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.033466782282280644,
-            "min": 0.031037968918507065,
-            "max": 0.045259725838980594,
-            "count": 17
+            "value": 0.02162035130895674,
+            "min": 0.01450827432796359,
+            "max": 0.026932200510909252,
+            "count": 8
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.4805453573571867,
-            "min": 2.4289718523650663,
-            "max": 4.163894777186215,
-            "count": 17
+            "value": 2.8106456701643765,
+            "min": 0.36270685819908977,
+            "max": 2.9356098556891084,
+            "count": 8
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 8
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 8
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06930674264174892,
-            "min": 0.0660624019059112,
-            "max": 0.07305593902510919,
-            "count": 17
+            "value": 0.045205598968702056,
+            "min": 0.04513349834208687,
+            "max": 0.05072030359828592,
+            "count": 7
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.48514719849224247,
-            "min": 0.2713861706738085,
-            "max": 0.5569559877413217,
-            "count": 17
+            "value": 0.31643919278091437,
+            "min": 0.3159344883946081,
+            "max": 0.40231775108487433,
+            "count": 7
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01782448553732777,
-            "min": 0.014894103345987494,
-            "max": 0.018641736482021946,
-            "count": 17
+            "value": 0.01756046380614862,
+            "min": 0.01689078080843213,
+            "max": 0.018238895967457945,
+            "count": 7
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.12477139876129438,
-            "min": 0.06648991553208701,
-            "max": 0.13552801926723784,
-            "count": 17
+            "value": 0.12292324664304033,
+            "min": 0.11823546565902493,
+            "max": 0.13659650496636316,
+            "count": 7
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.8900418938285686e-06,
-            "min": 2.8900418938285686e-06,
-            "max": 9.789406736866664e-05,
-            "count": 17
+            "value": 4.547376405999977e-07,
+            "min": 4.547376405999977e-07,
+            "max": 6.504610162150001e-06,
+            "count": 7
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 2.023029325679998e-05,
-            "min": 2.023029325679998e-05,
-            "max": 0.0006530248823252,
-            "count": 17
+            "value": 3.183163484199984e-06,
+            "min": 3.183163484199984e-06,
+            "max": 5.2036881297200007e-05,
+            "count": 7
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10096331428571428,
-            "min": 0.10096331428571428,
-            "max": 0.13263133333333338,
-            "count": 17
+            "value": 0.10045463809523807,
+            "min": 0.10045463809523807,
+            "max": 0.10650451666666667,
+            "count": 7
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 0.7067432,
-            "min": 0.5305253333333335,
-            "max": 1.0161251999999998,
-            "count": 17
+            "value": 0.7031824666666665,
+            "min": 0.7031824666666665,
+            "max": 0.8520361333333334,
+            "count": 7
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00010623509714285705,
-            "min": 0.00010623509714285705,
-            "max": 0.003269870200000001,
-            "count": 17
+            "value": 1.450091714285712e-05,
+            "min": 1.450091714285712e-05,
+            "max": 7.4394715e-05,
+            "count": 7
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0007436456799999994,
-            "min": 0.0007436456799999994,
-            "max": 0.02181571252,
-            "count": 17
+            "value": 0.00010150641999999984,
+            "min": 0.00010150641999999984,
+            "max": 0.00059515772,
+            "count": 7
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.010506981983780861,
-            "min": 0.010506981983780861,
-            "max": 0.01345684751868248,
-            "count": 17
+            "value": 0.009293955750763416,
+            "min": 0.008975865319371223,
+            "max": 0.009324299171566963,
+            "count": 7
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.07354887574911118,
-            "min": 0.05382739007472992,
-            "max": 0.10081358999013901,
-            "count": 17
-        },
-        "Pyramids.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 17
-        },
-        "Pyramids.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 17
+            "value": 0.06505768746137619,
+            "min": 0.06283105909824371,
+            "max": 0.07334689050912857,
+            "count": 7
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1736607952",
+        "start_time_seconds": "1736614884",
         "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1736609298"
+        "end_time_seconds": "1736615475"
     },
-    "total": 1346.8122431600004,
+    "total": 591.3225794409991,
     "count": 1,
-    "self": 0.49064115000010133,
+    "self": 0.7973925389997021,
     "children": {
         "run_training.setup": {
-            "total": 0.05665517500028727,
+            "total": 0.05759276599928853,
             "count": 1,
-            "self": 0.05665517500028727
+            "self": 0.05759276599928853
         },
         "TrainerController.start_learning": {
-            "total": 1346.264946835,
+            "total": 590.4675941360001,
             "count": 1,
-            "self": 0.8521974178802338,
+            "self": 0.39906842290110944,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.1636394279998967,
+                    "total": 3.1235094540006685,
                     "count": 1,
-                    "self": 2.1636394279998967
+                    "self": 3.1235094540006685
                 },
                 "TrainerController.advance": {
-                    "total": 1343.1521764261192,
-                    "count": 32661,
-                    "self": 0.8538884681161107,
+                    "total": 586.819589131097,
+                    "count": 14188,
+                    "self": 0.4218017009425239,
                     "children": {
                         "env_step": {
-                            "total": 985.9300335769713,
-                            "count": 32661,
-                            "self": 901.4416387460383,
+                            "total": 466.5465965630483,
+                            "count": 14188,
+                            "self": 426.67460349303656,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 83.98413710592376,
-                                    "count": 32661,
-                                    "self": 2.6045166798776336,
+                                    "total": 39.630197194972425,
+                                    "count": 14188,
+                                    "self": 1.191651979848757,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 81.37962042604613,
-                                            "count": 31375,
-                                            "self": 81.37962042604613
+                                            "total": 38.43854521512367,
+                                            "count": 13536,
+                                            "self": 38.43854521512367
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.5042577250092108,
-                                    "count": 32661,
+                                    "total": 0.24179587503931543,
+                                    "count": 14188,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1342.9793836750478,
-                                            "count": 32661,
+                                            "total": 588.8598102130964,
+                                            "count": 14188,
                                             "is_parallel": true,
-                                            "self": 509.44961395605924,
+                                            "self": 192.91342673410145,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002090751000196178,
+                                                            "total": 0.002846036999471835,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007156400001804286,
+                                                            "self": 0.0009063310008059489,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013751110000157496,
+                                                                    "total": 0.001939705998665886,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013751110000157496
+                                                                    "self": 0.001939705998665886
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05830848799996602,
+                                                            "total": 0.11663748899991333,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006312850000540493,
+                                                            "self": 0.005320938000295428,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004887700001745543,
+                                                                    "total": 0.0005124399995111162,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004887700001745543
+                                                                    "self": 0.0005124399995111162
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05532371299977967,
+                                                                    "total": 0.10718975000054343,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05532371299977967
+                                                                    "self": 0.10718975000054343
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018647199999577424,
+                                                                    "total": 0.0036143609995633597,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00046967800062702736,
+                                                                    "self": 0.002300742997249472,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001395041999330715,
+                                                                            "total": 0.0013136180023138877,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001395041999330715
+                                                                            "self": 0.0013136180023138877
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 833.5297697189885,
-                                                    "count": 32660,
+                                                    "total": 395.9463834789949,
+                                                    "count": 14187,
                                                     "is_parallel": true,
-                                                    "self": 17.9211746969263,
+                                                    "self": 8.27391039919712,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 12.497033008085964,
-                                                            "count": 32660,
+                                                            "total": 5.66011124700708,
+                                                            "count": 14187,
                                                             "is_parallel": true,
-                                                            "self": 12.497033008085964
+                                                            "self": 5.66011124700708
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 748.6699052399786,
-                                                            "count": 32660,
+                                                            "total": 357.27115853094074,
+                                                            "count": 14187,
                                                             "is_parallel": true,
-                                                            "self": 748.6699052399786
+                                                            "self": 357.27115853094074
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 54.44165677399769,
-                                                            "count": 32660,
+                                                            "total": 24.741203301849964,
+                                                            "count": 14187,
                                                             "is_parallel": true,
-                                                            "self": 11.600781844944777,
+                                                            "self": 5.356703152297996,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 42.840874929052916,
-                                                                    "count": 261280,
+                                                                    "total": 19.384500149551968,
+                                                                    "count": 113496,
                                                                     "is_parallel": true,
-                                                                    "self": 42.840874929052916
+                                                                    "self": 19.384500149551968
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 356.3682543810319,
-                            "count": 32661,
-                            "self": 1.7904080970311043,
+                            "total": 119.8511908671062,
+                            "count": 14188,
+                            "self": 0.85680559807588,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 65.51803872100072,
-                                    "count": 32661,
-                                    "self": 65.39194805300076,
+                                    "total": 27.788448726028946,
+                                    "count": 14188,
+                                    "self": 27.60438441102815,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.12609066799996071,
+                                            "total": 0.18406431500079634,
                                             "count": 1,
-                                            "self": 0.12609066799996071
+                                            "self": 0.18406431500079634
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 289.05980756300005,
-                                    "count": 118,
-                                    "self": 163.72242092500665,
+                                    "total": 91.20593654300137,
+                                    "count": 50,
+                                    "self": 60.63762731401221,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 125.3373866379934,
-                                            "count": 11496,
-                                            "self": 125.3373866379934
+                                            "total": 30.568309228989165,
+                                            "count": 2430,
+                                            "self": 30.568309228989165
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.082000380847603e-06,
+                    "total": 1.1990014172624797e-06,
                     "count": 1,
-                    "self": 1.082000380847603e-06
+                    "self": 1.1990014172624797e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0969324810002945,
+                    "total": 0.12542592899990268,
                     "count": 1,
-                    "self": 0.0019970160001321346,
+                    "self": 0.003000004000568879,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09493546500016237,
+                            "total": 0.1224259249993338,
                             "count": 1,
-                            "self": 0.09493546500016237
+                            "self": 0.1224259249993338
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 999914,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999914.onnx",
-                "reward": 1.094299964606762,
-                "creation_time": 1736607832.1963856,
+                "steps": 1999957,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999957.onnx",
+                "reward": 1.7079999910460577,
+                "creation_time": 1736612585.6080968,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999914.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1999957.pt"
                 ]
             },
             {
-                "steps": 1000042,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000042.onnx",
-                "reward": 1.094299964606762,
-                "creation_time": 1736607832.3471467,
+                "steps": 2499814,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499814.onnx",
+                "reward": 1.7711666425069172,
+                "creation_time": 1736613972.1583915,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000042.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2499814.pt"
                 ]
             },
             {
-                "steps": 1000042,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000042.onnx",
-                "reward": null,
-                "creation_time": 1736607876.3441033,
+                "steps": 2785932,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2785932.onnx",
+                "reward": 1.7967142462730408,
+                "creation_time": 1736614789.8198874,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000042.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2785932.pt"
                 ]
             },
             {
-                "steps": 1499976,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499976.onnx",
-                "reward": 1.7212221887376573,
-                "creation_time": 1736609298.2595682,
+                "steps": 2999867,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999867.onnx",
+                "reward": 1.8234999775886536,
+                "creation_time": 1736615474.792497,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1499976.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2999867.pt"
                 ]
             },
             {
-                "steps": 1500161,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1500161.onnx",
-                "reward": 1.7306999683380127,
-                "creation_time": 1736609298.3708541,
+                "steps": 3000197,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000197.onnx",
+                "reward": 1.7726666529973347,
+                "creation_time": 1736615474.9542418,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1500161.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-3000197.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1500161,
+            "steps": 3000197,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7306999683380127,
-            "creation_time": 1736609298.3708541,
+            "reward": 1.7726666529973347,
+            "creation_time": 1736615474.9542418,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1500161.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000197.pt"
             ]
         }
     },