First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398f4341096160367e209066f28646774a621e3fcc11a75c435aae9ac3a3e87e
+oid sha256:63fd804040d83c19cd5e64fb1f57ebea7e46ca94a06546987ae789f7121069d5
 size 1420238

Pyramids/Pyramids-100085.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63fd804040d83c19cd5e64fb1f57ebea7e46ca94a06546987ae789f7121069d5
+size 1420238

Pyramids/Pyramids-100085.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f1fa159f8a1b648c376f9c1176d7fc23aea8c0064a15604157665a92090fde
+size 10002989

Pyramids/Pyramids-42240.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a65c17dd8a40466d4a7ca6923dfee1a2b6a9fd77643681d283f2b77be69989
+size 1420238

Pyramids/Pyramids-42240.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01b3b83a11df8475558d5d2137ca28edbc570b3c14f571bb38945adc1ca4196
+size 8656094

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a40f4cb287bcbe4286a8c27688b9fb07ede76e69a8e7d22e7ccf919fc6fa93d
-size 8655778
+oid sha256:e3dcdca06932e691b975f952d234432745f7a2571e2fd3c24071ac42f8dfc0d2
+size 10002594

Pyramids/events.out.tfevents.1716714196.9bd833adf9b7.24327.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c369eb33dc4905e9c9c9e57bfd270f718fc1ed1c8564c66bd541fcb8667e456
+size 37165

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": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": false, "force": true, "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": 0.0005, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.02, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0005, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 100000, "time_horizon": 128, "summary_freq": 5000, "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": false, "force": true, "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: 0.0005
       beta: 0.01
       epsilon: 0.2
       lambd: 0.95
@@ -35,25 +35,25 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-      rnd:
+      curiosity:
         gamma: 0.99
-        strength: 0.01
+        strength: 0.02
         network_settings:
           normalize: false
-          hidden_units: 64
-          num_layers: 3
+          hidden_units: 256
+          num_layers: 2
           vis_encode_type: simple
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
-        learning_rate: 0.0001
+        learning_rate: 0.0005
         encoding_size: null
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 3000000
+    max_steps: 100000
     time_horizon: 128
-    summary_freq: 30000
+    summary_freq: 5000
     threaded: false
     self_play: null
     behavioral_cloning: null

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55488 [Flags] 2 [Guid] 1910078472 [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] 55111 [Flags] 2 [Guid] 3873199685 [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  0.095 seconds
+- Completed reload, in  0.096 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: 0.821976 ms
+UnloadTime: 0.975347 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]: 2955 frames, [32.0 KB-64.0 KB]: 1217 frames, [64.0 KB-128.0 KB]: 157 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1225 frames, [32.0 KB-64.0 KB]: 588 frames, [64.0 KB-128.0 KB]: 74 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
@@ -146,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -204,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 4031 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 1589 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 12107
+  Peak main deferred allocation count 11929
     [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]: 4328 frames, [32.0 MB-64.0 MB]: 1 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 1887 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 32.6 MB
+      Peak Allocated memory 31.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 4330 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1888 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.9 MB
+      Peak Allocated memory 22.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4329 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1887 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]: 4330 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 1888 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]: 4031 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 1589 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]: 4329 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 1887 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.2 MB
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -290,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 4330 frames
+      Peak usage frame count: [0-1.0 KB]: 1888 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]: 4330 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 1888 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]: 4330 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 1888 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 28.5 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":1716713221513,"processId":18075,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1716714437214,"processId":24360,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,249 +2,261 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 1.0261327028274536,
-            "min": 0.7610291838645935,
-            "max": 1.4961549043655396,
-            "count": 7
+            "value": 0.6451210975646973,
+            "min": 0.6451210975646973,
+            "max": 1.6069170236587524,
+            "count": 20
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 30734.7265625,
-            "min": 22794.345703125,
-            "max": 45387.35546875,
-            "count": 7
+            "value": 3014.005859375,
+            "min": 2957.91796875,
+            "max": 9872.8984375,
+            "count": 20
         },
         "Pyramids.Step.mean": {
-            "value": 209929.0,
-            "min": 29952.0,
-            "max": 209929.0,
-            "count": 7
+            "value": 99957.0,
+            "min": 4992.0,
+            "max": 99957.0,
+            "count": 20
         },
         "Pyramids.Step.sum": {
-            "value": 209929.0,
-            "min": 29952.0,
-            "max": 209929.0,
-            "count": 7
+            "value": 99957.0,
+            "min": 4992.0,
+            "max": 99957.0,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.10188606381416321,
-            "min": -0.10188606381416321,
-            "max": -0.06755714118480682,
-            "count": 7
+            "value": -0.10700247436761856,
+            "min": -0.11036466807126999,
+            "max": 0.19310301542282104,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -24.452655792236328,
-            "min": -24.452655792236328,
-            "max": -16.28127098083496,
-            "count": 7
-        },
-        "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.02070438116788864,
-            "min": 0.02070438116788864,
-            "max": 0.3795851469039917,
-            "count": 7
-        },
-        "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 4.969051361083984,
-            "min": 4.969051361083984,
-            "max": 89.96167755126953,
-            "count": 7
+            "value": -4.280098915100098,
+            "min": -4.524951457977295,
+            "max": 7.531017780303955,
+            "count": 20
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.31208768486976624,
+            "min": -0.11871524900197983,
+            "max": 0.5101918578147888,
+            "count": 20
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.sum": {
+            "value": 12.48350715637207,
+            "min": -4.629894733428955,
+            "max": 21.294876098632812,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06948383712092293,
-            "min": 0.0669552986946384,
-            "max": 0.0718437648804213,
-            "count": 7
+            "value": 0.06758057010979622,
+            "min": 0.060139786034900077,
+            "max": 0.08101109993355028,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.8338060454510752,
-            "min": 0.502906354162949,
-            "max": 0.9147761987872329,
-            "count": 7
+            "value": 0.20274171032938865,
+            "min": 0.060139786034900077,
+            "max": 0.20274171032938865,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.00016674057673984985,
-            "min": 0.00012009727553268412,
-            "max": 0.00663446226275563,
-            "count": 7
+            "value": 0.00029973042170878004,
+            "min": 0.00029973042170878004,
+            "max": 0.014868051817757078,
+            "count": 20
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.0020008869208781982,
-            "min": 0.0014411673063922095,
-            "max": 0.046441235839289406,
-            "count": 7
+            "value": 0.0008991912651263402,
+            "min": 0.00041016983324844463,
+            "max": 0.016111305192002785,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 0.0002805339731553444,
-            "min": 0.0002805339731553444,
-            "max": 0.00029838354339596195,
-            "count": 7
+            "value": 1.109509778100002e-05,
+            "min": 1.109509778100002e-05,
+            "max": 0.000479520004096,
+            "count": 20
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.003366407677864133,
-            "min": 0.0020886848037717336,
-            "max": 0.0037253763582078994,
-            "count": 7
+            "value": 3.328529334300006e-05,
+            "min": 3.328529334300006e-05,
+            "max": 0.0007785600442879999,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.19351132222222225,
-            "min": 0.19351132222222225,
-            "max": 0.19946118095238097,
-            "count": 7
+            "value": 0.10221900000000002,
+            "min": 0.10221900000000002,
+            "max": 0.19590400000000005,
+            "count": 20
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 2.322135866666667,
-            "min": 1.3962282666666668,
-            "max": 2.5417921,
-            "count": 7
+            "value": 0.30665700000000007,
+            "min": 0.13778899999999994,
+            "max": 0.38347300000000006,
+            "count": 20
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.009351781089999999,
-            "min": 0.009351781089999999,
-            "max": 0.009946171977142856,
-            "count": 7
+            "value": 0.00023167810000000047,
+            "min": 0.00023167810000000047,
+            "max": 0.0095908096,
+            "count": 20
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.11222137307999999,
-            "min": 0.06962320384,
-            "max": 0.12418503079000001,
-            "count": 7
-        },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.03376156836748123,
-            "min": 0.03376156836748123,
-            "max": 0.3565838634967804,
-            "count": 7
-        },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.4051388204097748,
-            "min": 0.4051388204097748,
-            "max": 2.496087074279785,
-            "count": 7
+            "value": 0.0006950343000000014,
+            "min": 0.0006950343000000014,
+            "max": 0.015575628800000001,
+            "count": 20
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.1331191056088549,
+            "min": 0.13191234056527415,
+            "max": 1.062101550400257,
+            "count": 20
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.sum": {
+            "value": 0.3993573168265647,
+            "min": 0.1845689576960379,
+            "max": 1.062101550400257,
+            "count": 20
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.mean": {
+            "value": 0.19341666065103527,
+            "min": 0.19341666065103527,
+            "max": 1.0087984967976809,
+            "count": 20
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.sum": {
+            "value": 0.5802499819531058,
+            "min": 0.2827631707793923,
+            "max": 1.0708979216093817,
+            "count": 20
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
         },
         "Pyramids.Environment.EpisodeLength.mean": {
             "value": 999.0,
-            "min": 976.6363636363636,
+            "min": 514.0,
             "max": 999.0,
-            "count": 7
+            "count": 10
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30969.0,
-            "min": 15984.0,
-            "max": 32229.0,
-            "count": 7
+            "value": 14985.0,
+            "min": 514.0,
+            "max": 15984.0,
+            "count": 10
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.9999355356539449,
+            "value": -1.0000000521540642,
             "min": -1.0000000521540642,
-            "max": -0.8718875516206026,
-            "count": 7
+            "max": 1.4860000014305115,
+            "count": 12
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -30.998001605272293,
-            "min": -31.997201651334763,
-            "max": -16.000000834465027,
-            "count": 7
+            "value": -6.000000312924385,
+            "min": -16.000000834465027,
+            "max": 2.375999867916107,
+            "count": 12
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.9999355356539449,
+            "value": -1.0000000521540642,
             "min": -1.0000000521540642,
-            "max": -0.8718875516206026,
-            "count": 7
+            "max": 1.4860000014305115,
+            "count": 12
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -30.998001605272293,
-            "min": -31.997201651334763,
-            "max": -16.000000834465027,
-            "count": 7
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.35670630639839557,
-            "min": 0.35670630639839557,
-            "max": 6.936993133276701,
-            "count": 7
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 11.057895498350263,
-            "min": 11.057895498350263,
-            "max": 110.99189013242722,
-            "count": 7
+            "value": -6.000000312924385,
+            "min": -16.000000834465027,
+            "max": 2.375999867916107,
+            "count": 12
         },
-        "Pyramids.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 7
+        "Pyramids.Policy.CuriosityReward.mean": {
+            "value": 2.8052185798684754,
+            "min": 2.8052185798684754,
+            "max": 6.720910437405109,
+            "count": 12
         },
-        "Pyramids.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 7
+        "Pyramids.Policy.CuriosityReward.sum": {
+            "value": 16.831311479210854,
+            "min": 3.1243360936641693,
+            "max": 107.53456699848175,
+            "count": 12
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1716712723",
+        "start_time_seconds": "1716714195",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Pyramids.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "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": "1716713221"
+        "end_time_seconds": "1716714437"
     },
-    "total": 497.95184621299995,
+    "total": 241.32956991600076,
     "count": 1,
-    "self": 0.33572314199955144,
+    "self": 0.5013118150000082,
     "children": {
         "run_training.setup": {
-            "total": 0.05327586700059328,
+            "total": 0.056518850000429666,
             "count": 1,
-            "self": 0.05327586700059328
+            "self": 0.056518850000429666
         },
         "TrainerController.start_learning": {
-            "total": 497.5628472039998,
+            "total": 240.77173925100033,
             "count": 1,
-            "self": 0.42107916293934977,
+            "self": 0.18175960001099156,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.2582648210000116,
+                    "total": 2.4149710379997487,
                     "count": 1,
-                    "self": 2.2582648210000116
+                    "self": 2.4149710379997487
                 },
                 "TrainerController.advance": {
-                    "total": 494.69077947705955,
-                    "count": 14455,
-                    "self": 0.4103215251379879,
+                    "total": 238.05032934099017,
+                    "count": 6304,
+                    "self": 0.2095663039754072,
                     "children": {
                         "env_step": {
-                            "total": 342.7020342810283,
-                            "count": 14455,
-                            "self": 304.0636459290081,
+                            "total": 155.05327726704854,
+                            "count": 6304,
+                            "self": 136.69235677504003,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 38.40106151494365,
-                                    "count": 14455,
-                                    "self": 1.2628076679593505,
+                                    "total": 18.247605549026957,
+                                    "count": 6304,
+                                    "self": 0.5990804590810512,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 37.1382538469843,
-                                            "count": 14434,
-                                            "self": 37.1382538469843
+                                            "total": 17.648525089945906,
+                                            "count": 6292,
+                                            "self": 17.648525089945906
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.23732683707657998,
-                                    "count": 14454,
+                                    "total": 0.11331494298156031,
+                                    "count": 6304,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 496.0590658679739,
-                                            "count": 14454,
+                                            "total": 240.0926715700234,
+                                            "count": 6304,
                                             "is_parallel": true,
-                                            "self": 225.6414582790867,
+                                            "self": 118.93710902202383,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0023437170002580388,
+                                                            "total": 0.002296657000442792,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006748129990228335,
+                                                            "self": 0.0006495540001196787,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0016689040012352052,
+                                                                    "total": 0.0016471030003231135,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0016689040012352052
+                                                                    "self": 0.0016471030003231135
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07444514200051344,
+                                                            "total": 0.049303064000014274,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006639210005232599,
+                                                            "self": 0.0006382899991876911,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004881469994870713,
+                                                                    "total": 0.000485536999804026,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004881469994870713
+                                                                    "self": 0.000485536999804026
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.07153648599978624,
+                                                                    "total": 0.0463892420002594,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.07153648599978624
+                                                                    "self": 0.0463892420002594
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017565880007168744,
+                                                                    "total": 0.001789995000763156,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00038292299996101065,
+                                                                    "self": 0.0003914800026905141,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013736650007558637,
+                                                                            "total": 0.001398514998072642,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013736650007558637
+                                                                            "self": 0.001398514998072642
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +315,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 270.4176075888872,
-                                                    "count": 14453,
+                                                    "total": 121.15556254799958,
+                                                    "count": 6303,
                                                     "is_parallel": true,
-                                                    "self": 8.779477905871317,
+                                                    "self": 3.98279508106134,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 6.000877709031556,
-                                                            "count": 14453,
+                                                            "total": 2.6460406800015335,
+                                                            "count": 6303,
                                                             "is_parallel": true,
-                                                            "self": 6.000877709031556
+                                                            "self": 2.6460406800015335
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 230.4200480139807,
-                                                            "count": 14453,
+                                                            "total": 103.0294933479372,
+                                                            "count": 6303,
                                                             "is_parallel": true,
-                                                            "self": 230.4200480139807
+                                                            "self": 103.0294933479372
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 25.217203960003644,
-                                                            "count": 14453,
+                                                            "total": 11.497233438999501,
+                                                            "count": 6303,
                                                             "is_parallel": true,
-                                                            "self": 5.352794815871675,
+                                                            "self": 2.431688196011237,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 19.86440914413197,
-                                                                    "count": 115624,
+                                                                    "total": 9.065545242988264,
+                                                                    "count": 50424,
                                                                     "is_parallel": true,
-                                                                    "self": 19.86440914413197
+                                                                    "self": 9.065545242988264
                                                                 }
                                                             }
                                                         }
@@ -343,24 +355,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 151.57842367089324,
-                            "count": 14454,
-                            "self": 0.5691707298756228,
+                            "total": 82.78748576996622,
+                            "count": 6304,
+                            "self": 0.25155939395790483,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 29.43333330902169,
-                                    "count": 14454,
-                                    "self": 29.43333330902169
+                                    "total": 12.518190540013165,
+                                    "count": 6304,
+                                    "self": 12.518190540013165
                                 },
                                 "_update_policy": {
-                                    "total": 121.57591963199593,
-                                    "count": 82,
-                                    "self": 70.89063433302454,
+                                    "total": 70.01773583599515,
+                                    "count": 33,
+                                    "self": 46.00202858499506,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 50.685285298971394,
-                                            "count": 5295,
-                                            "self": 50.685285298971394
+                                            "total": 24.015707251000094,
+                                            "count": 2325,
+                                            "self": 24.015707251000094
                                         }
                                     }
                                 }
@@ -369,19 +381,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.7060001482605003e-06,
+                    "total": 8.669994713272899e-07,
                     "count": 1,
-                    "self": 1.7060001482605003e-06
+                    "self": 8.669994713272899e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.19272203700074897,
+                    "total": 0.12467840499994054,
                     "count": 1,
-                    "self": 0.0033570360001249355,
+                    "self": 0.0019627969995781314,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.18936500100062403,
+                            "total": 0.12271560800036241,
                             "count": 1,
-                            "self": 0.18936500100062403
+                            "self": 0.12271560800036241
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,22 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 230001,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-230001.onnx",
+                "steps": 100085,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-100085.onnx",
                 "reward": null,
-                "creation_time": 1716713221.2178004,
+                "creation_time": 1716714436.7733414,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-230001.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-100085.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 230001,
+            "steps": 100085,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
             "reward": null,
-            "creation_time": 1716713221.2178004,
+            "creation_time": 1716714436.7733414,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-230001.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-100085.pt"
             ]
         }
     },