Baseline

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46669cec4c0d42172553fab8315adbd9037ce091249af74a0eb5712c067bbf52
+oid sha256:b2006d5d05b76f3232a54a649b5207721a83da79be73105cb16f78f1e09dd642
 size 1418184

Pyramids/Pyramids-1499965.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27e2e8d9633b3c92ac967b973d1c27fc7917924bb13600a21bd1b8007457abc
+size 1418184

Pyramids/Pyramids-1499965.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b64351c29eb369d7aec75f8016c7458b06be9b6f575f0674ed5aa6675f6ce7e
+size 8650990

Pyramids/Pyramids-1999884.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e222d9bca26b556c1aeba7d28cff795ed4b71bad6324f495a6460065fda4a935
+size 1418184

Pyramids/Pyramids-1999884.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcacacfeb21613ded2846dce1fcd92a6cfda00f082217ccce2a9a899e6bacbef
+size 8650990

Pyramids/Pyramids-2499989.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35fba3e753af5b832a357c12501ffd78670f0dc07999e13da8d03c30b69ca06
+size 1418184

Pyramids/Pyramids-2499989.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6feba33e4879783d3152ece7b9424bdc268b4c7f320e67602454bee04d6821
+size 8650990

Pyramids/Pyramids-2999902.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2006d5d05b76f3232a54a649b5207721a83da79be73105cb16f78f1e09dd642
+size 1418184

Pyramids/Pyramids-2999902.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:313b2bff776600a80a304fead0b5fea86af290899246754290ddea01736638d7
+size 8650990

Pyramids/Pyramids-3000030.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2006d5d05b76f3232a54a649b5207721a83da79be73105cb16f78f1e09dd642
+size 1418184

Pyramids/Pyramids-3000030.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200bd079b4ca5643fae5c358cd255e9ce0d77c52046b6dd36defd793f72309da
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdac669b29dc54e84b9779b2bc8292d333aed7c99e47e3c1b94a83d647b0fd5d
+oid sha256:200bd079b4ca5643fae5c358cd255e9ce0d77c52046b6dd36defd793f72309da
 size 8650990

Pyramids/events.out.tfevents.1691544181.muon.885.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6a01b18b72bd53784db48412d7722f687cdd73d4c5da54b12b58bd64f532dc
+size 896379

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.15, "lambd": 0.95, "num_epoch": 5, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "envs/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids-01", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "envs/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids-02", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,13 +3,13 @@ behaviors:
   Pyramids:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 256
+      batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.005
-      epsilon: 0.15
+      beta: 0.01
+      epsilon: 0.2
       lambd: 0.95
-      num_epoch: 5
+      num_epoch: 3
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -77,7 +77,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids-01
+  run_id: Pyramids-02
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/home/patonw/code/Unity/ml-agents/envs/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/home/patonw/code/Unity/ml-agents/envs/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 3 interfaces on host : 0) 10.10.10.100 1) 192.168.56.1 2) 172.17.0.1
-Multi-casting "[IP] 10.10.10.100 [Port] 55445 [Flags] 2 [Guid] 1930785067 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,10.10.10.100) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 10.10.10.100 [Port] 55365 [Flags] 2 [Guid] 2112073968 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,10.10.10.100) [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)
@@ -46,7 +46,7 @@ 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: 0.422803 ms
+UnloadTime: 0.422713 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 12 worker threads for Enlighten.
@@ -54,7 +54,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4088 frames, [32.0 KB-64.0 KB]: 11339 frames, [64.0 KB-128.0 KB]: 3341 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 6583 frames, [32.0 KB-64.0 KB]: 34325 frames, [64.0 KB-128.0 KB]: 15356 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
@@ -174,11 +174,6 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 6]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
-      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -189,9 +184,9 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_EnlightenWorker] x 12
@@ -204,6 +199,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
@@ -257,7 +257,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 1]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -295,28 +295,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55966 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 13352
+  Peak main deferred allocation count 12835
     [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]: 18768 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56264 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.3 MB
+      Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56265 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 28.9 MB
+      Peak Allocated memory 29.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -345,13 +345,13 @@ 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]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56264 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]: 18769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 56265 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -363,13 +363,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55966 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]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 56264 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
@@ -381,19 +381,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18769 frames
+      Peak usage frame count: [0-1.0 KB]: 56265 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]: 18769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56265 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: [32.0 KB-64.0 KB]: 18769 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 56265 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 47.1 KB
@@ -402,4 +402,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1691539693565,"processId":487,"allocatedMemory":1998189,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":35076},{"Manager":29067},{"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":10336},{"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":1691546847957,"processId":958,"allocatedMemory":1998189,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":35076},{"Manager":29067},{"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":10336},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.33127880096435547,
-            "min": 0.3272187113761902,
-            "max": 1.4771008491516113,
-            "count": 33
+            "value": 0.18317589163780212,
+            "min": 0.16339467465877533,
+            "max": 1.4302423000335693,
+            "count": 100
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 9869.4580078125,
-            "min": 9769.44140625,
-            "max": 44809.33203125,
-            "count": 33
+            "value": 5471.830078125,
+            "min": 4920.140625,
+            "max": 43387.83203125,
+            "count": 100
         },
         "Pyramids.Step.mean": {
-            "value": 989872.0,
+            "value": 2999902.0,
             "min": 29952.0,
-            "max": 989872.0,
-            "count": 33
+            "max": 2999902.0,
+            "count": 100
         },
         "Pyramids.Step.sum": {
-            "value": 989872.0,
+            "value": 2999902.0,
             "min": 29952.0,
-            "max": 989872.0,
-            "count": 33
+            "max": 2999902.0,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5954773426055908,
-            "min": -0.17912505567073822,
-            "max": 0.667241632938385,
-            "count": 33
+            "value": 0.7723481059074402,
+            "min": -0.10346413403749466,
+            "max": 0.8570897579193115,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 166.13818359375,
-            "min": -42.45263671875,
-            "max": 191.49835205078125,
-            "count": 33
+            "value": 228.6150360107422,
+            "min": -24.934856414794922,
+            "max": 261.4123840332031,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.022388316690921783,
-            "min": -0.01222789566963911,
-            "max": 0.4052538573741913,
-            "count": 33
+            "value": 0.013043629005551338,
+            "min": 0.0030720990616828203,
+            "max": 0.43157798051834106,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 6.246340274810791,
-            "min": -3.399354934692383,
-            "max": 96.045166015625,
-            "count": 33
+            "value": 3.8609142303466797,
+            "min": 0.8509714603424072,
+            "max": 102.28398132324219,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.046257890331824966,
-            "min": 0.044582932438268996,
-            "max": 0.05127516522693138,
-            "count": 33
+            "value": 0.07008140640035788,
+            "min": 0.06315222284896821,
+            "max": 0.07610215950602045,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.6476104646455495,
-            "min": 0.3542371658400433,
-            "max": 0.7691274784039707,
-            "count": 33
+            "value": 1.0512210960053683,
+            "min": 0.49090916727854866,
+            "max": 1.1415323925903067,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.015370714325191716,
-            "min": 0.0005580240246347654,
-            "max": 0.015486346623427901,
-            "count": 33
+            "value": 0.015848874939709073,
+            "min": 0.00013317596300608172,
+            "max": 0.01689037030102315,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.21519000055268403,
-            "min": 0.004464192197078123,
-            "max": 0.2182482191827148,
-            "count": 33
+            "value": 0.2377331240956361,
+            "min": 0.0015981115560729808,
+            "max": 0.24140345549676567,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.71444742855e-06,
-            "min": 7.71444742855e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 1.487032837688891e-06,
+            "min": 1.487032837688891e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010800226399969999,
-            "min": 0.00010800226399969999,
-            "max": 0.0033690487769837997,
-            "count": 33
+            "value": 2.2305492565333364e-05,
+            "min": 2.2305492565333364e-05,
+            "max": 0.003759455746848133,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10128572500000001,
-            "min": 0.10128572500000001,
-            "max": 0.14919177142857146,
-            "count": 33
+            "value": 0.10049564444444443,
+            "min": 0.10049564444444443,
+            "max": 0.19946118095238097,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4180001500000001,
-            "min": 1.0345568000000003,
-            "max": 1.9463147999999997,
-            "count": 33
+            "value": 1.5074346666666665,
+            "min": 1.3962282666666668,
+            "max": 2.7225589000000006,
+            "count": 100
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.000138315355,
-            "min": 0.000138315355,
-            "max": 0.004919338788571428,
-            "count": 33
+            "value": 5.9514880000000075e-05,
+            "min": 5.9514880000000075e-05,
+            "max": 0.009946171977142856,
+            "count": 100
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0019364149700000003,
-            "min": 0.0019364149700000003,
-            "max": 0.056168508379999996,
-            "count": 33
+            "value": 0.0008927232000000011,
+            "min": 0.0008927232000000011,
+            "max": 0.12532987148000002,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.012271500192582607,
-            "min": 0.012271500192582607,
-            "max": 0.4569520950317383,
-            "count": 33
+            "value": 0.006677953992038965,
+            "min": 0.006240218877792358,
+            "max": 0.5930566191673279,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.17180100083351135,
-            "min": 0.17180100083351135,
-            "max": 3.198664665222168,
-            "count": 33
+            "value": 0.10016930848360062,
+            "min": 0.08736306428909302,
+            "max": 4.15139627456665,
+            "count": 100
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 313.36842105263156,
-            "min": 288.83168316831683,
+            "value": 252.2991452991453,
+            "min": 218.91489361702128,
             "max": 999.0,
-            "count": 33
+            "count": 100
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29770.0,
+            "value": 29519.0,
             "min": 15984.0,
-            "max": 32605.0,
-            "count": 33
+            "max": 32769.0,
+            "count": 100
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6024041920900345,
+            "value": 1.713505968833581,
             "min": -1.0000000521540642,
-            "max": 1.7111683018726878,
-            "count": 33
+            "max": 1.7808521017432213,
+            "count": 100
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 152.22839824855328,
-            "min": -32.000001668930054,
-            "max": 172.82799848914146,
-            "count": 33
+            "value": 200.48019835352898,
+            "min": -31.99640166759491,
+            "max": 252.88099844753742,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6024041920900345,
+            "value": 1.713505968833581,
             "min": -1.0000000521540642,
-            "max": 1.7111683018726878,
-            "count": 33
+            "max": 1.7808521017432213,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 152.22839824855328,
-            "min": -32.000001668930054,
-            "max": 172.82799848914146,
-            "count": 33
+            "value": 200.48019835352898,
+            "min": -31.99640166759491,
+            "max": 252.88099844753742,
+            "count": 100
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.04020569168941093,
-            "min": 0.03845810438800225,
-            "max": 8.27740378677845,
-            "count": 33
+            "value": 0.017547774691538662,
+            "min": 0.014787722639880485,
+            "max": 11.427808299660683,
+            "count": 100
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.8195407104940386,
-            "min": 3.8195407104940386,
-            "max": 132.4384605884552,
-            "count": 33
+            "value": 2.0530896389100235,
+            "min": 1.892828497904702,
+            "max": 182.84493279457092,
+            "count": 100
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 100
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 100
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1691538847",
+        "start_time_seconds": "1691544180",
         "python_version": "3.9.0 | packaged by conda-forge | (default, Nov 26 2020, 07:57:39) \n[GCC 9.3.0]",
-        "command_line_arguments": "/home/patonw/code/Unity/ml-agents/.mamba/envs/my-mamba-environment/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env envs/Pyramids/Pyramids --run-id Pyramids-01 --no-graphics",
+        "command_line_arguments": "/home/patonw/code/Unity/ml-agents/.mamba/envs/my-mamba-environment/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env envs/Pyramids/Pyramids --run-id Pyramids-02 --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu113",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1691539693"
+        "end_time_seconds": "1691546848"
     },
-    "total": 845.7198406470006,
+    "total": 2667.2387524330006,
     "count": 1,
-    "self": 0.16761923100057174,
+    "self": 0.21785052700033702,
     "children": {
         "run_training.setup": {
-            "total": 0.009514155000033497,
+            "total": 0.009867504999419907,
             "count": 1,
-            "self": 0.009514155000033497
+            "self": 0.009867504999419907
         },
         "TrainerController.start_learning": {
-            "total": 845.542707261,
+            "total": 2667.011034401001,
             "count": 1,
-            "self": 0.5749882738628003,
+            "self": 1.9650581697751477,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.7861417519998213,
+                    "total": 2.850871491000362,
                     "count": 1,
-                    "self": 2.7861417519998213
+                    "self": 2.850871491000362
                 },
                 "TrainerController.advance": {
-                    "total": 842.1344997231372,
-                    "count": 64030,
-                    "self": 0.6102663591573219,
+                    "total": 2662.1478119632247,
+                    "count": 194784,
+                    "self": 1.9136386515147024,
                     "children": {
                         "env_step": {
-                            "total": 501.37763027988785,
-                            "count": 64030,
-                            "self": 447.6720702017292,
+                            "total": 1692.5154466116,
+                            "count": 194784,
+                            "self": 1486.4000926393492,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 53.31953210703523,
-                                    "count": 64030,
-                                    "self": 1.9278778510279153,
+                                    "total": 204.85600924948994,
+                                    "count": 194784,
+                                    "self": 5.960243603010895,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 51.391654256007314,
-                                            "count": 62563,
-                                            "self": 51.391654256007314
+                                            "total": 198.89576564647905,
+                                            "count": 187549,
+                                            "self": 198.89576564647905
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3860279711234398,
-                                    "count": 64030,
+                                    "total": 1.2593447227609431,
+                                    "count": 194784,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 844.552075363963,
-                                            "count": 64030,
+                                            "total": 2664.1007865956126,
+                                            "count": 194784,
                                             "is_parallel": true,
-                                            "self": 438.0853086501529,
+                                            "self": 1308.7857927869882,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0007753130003038677,
+                                                            "total": 0.0007852920007280773,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00023399200108542573,
+                                                            "self": 0.00023520399918197654,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.000541320999218442,
+                                                                    "total": 0.0005500880015461007,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000541320999218442
+                                                                    "self": 0.0005500880015461007
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.017454079999879468,
+                                                            "total": 0.017291787000431214,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00016867899921635399,
+                                                            "self": 0.00021072799972898792,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00020340399987617275,
+                                                                    "total": 0.00020643900097638834,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00020340399987617275
+                                                                    "self": 0.00020643900097638834
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.016547408000405994,
+                                                                    "total": 0.016191912000067532,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.016547408000405994
+                                                                    "self": 0.016191912000067532
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0005345890003809473,
+                                                                    "total": 0.0006827079996583052,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00013789099921268644,
+                                                                    "self": 0.000171674002558575,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0003966980011682608,
+                                                                            "total": 0.0005110339970997302,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0003966980011682608
+                                                                            "self": 0.0005110339970997302
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 406.4667667138101,
-                                                    "count": 64029,
+                                                    "total": 1355.3149938086244,
+                                                    "count": 194783,
                                                     "is_parallel": true,
-                                                    "self": 10.850232318574854,
+                                                    "self": 34.34300277039074,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 7.503647363024356,
-                                                            "count": 64029,
+                                                            "total": 23.092716686138374,
+                                                            "count": 194783,
                                                             "is_parallel": true,
-                                                            "self": 7.503647363024356
+                                                            "self": 23.092716686138374
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 356.40677039300135,
-                                                            "count": 64029,
+                                                            "total": 1198.34512067606,
+                                                            "count": 194783,
                                                             "is_parallel": true,
-                                                            "self": 356.40677039300135
+                                                            "self": 1198.34512067606
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 31.70611663920954,
-                                                            "count": 64029,
+                                                            "total": 99.5341536760352,
+                                                            "count": 194783,
                                                             "is_parallel": true,
-                                                            "self": 6.946485437675619,
+                                                            "self": 21.942711345516727,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 24.75963120153392,
-                                                                    "count": 512232,
+                                                                    "total": 77.59144233051848,
+                                                                    "count": 1558264,
                                                                     "is_parallel": true,
-                                                                    "self": 24.75963120153392
+                                                                    "self": 77.59144233051848
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 340.146603084092,
-                            "count": 64030,
-                            "self": 1.0386115870278445,
+                            "total": 967.71872670011,
+                            "count": 194784,
+                            "self": 3.6993494265625486,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 49.79324732306122,
-                                    "count": 64030,
-                                    "self": 49.68062957606071,
+                                    "total": 175.21312881762788,
+                                    "count": 194784,
+                                    "self": 174.86641048962883,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.11261774700051319,
-                                            "count": 2,
-                                            "self": 0.11261774700051319
+                                            "total": 0.34671832799904223,
+                                            "count": 6,
+                                            "self": 0.34671832799904223
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 289.31474417400295,
-                                    "count": 445,
-                                    "self": 210.7426778740255,
+                                    "total": 788.8062484559196,
+                                    "count": 1389,
+                                    "self": 478.2296473118313,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 78.57206629997745,
-                                            "count": 18895,
-                                            "self": 78.57206629997745
+                                            "total": 310.5766011440883,
+                                            "count": 68391,
+                                            "self": 310.5766011440883
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 6.609998308704235e-07,
+                    "total": 5.9100057114847e-07,
                     "count": 1,
-                    "self": 6.609998308704235e-07
+                    "self": 5.9100057114847e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.04707685100038361,
+                    "total": 0.047292186000049696,
                     "count": 1,
-                    "self": 0.0007262710005306872,
+                    "self": 0.0007333229987125378,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.046350579999852926,
+                            "total": 0.04655886300133716,
                             "count": 1,
-                            "self": 0.046350579999852926
+                            "self": 0.04655886300133716
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499954,
-                "file_path": "results/Pyramids-01/Pyramids/Pyramids-499954.onnx",
-                "reward": 1.5247499532997608,
-                "creation_time": 1691539257.786818,
+                "steps": 1499965,
+                "file_path": "results/Pyramids-02/Pyramids/Pyramids-1499965.onnx",
+                "reward": 1.765666663646698,
+                "creation_time": 1691545560.8058906,
                 "auxillary_file_paths": [
-                    "results/Pyramids-01/Pyramids/Pyramids-499954.pt"
+                    "results/Pyramids-02/Pyramids/Pyramids-1499965.pt"
                 ]
             },
             {
-                "steps": 999949,
-                "file_path": "results/Pyramids-01/Pyramids/Pyramids-999949.onnx",
-                "reward": 1.8086666415135066,
-                "creation_time": 1691539693.355373,
+                "steps": 1999884,
+                "file_path": "results/Pyramids-02/Pyramids/Pyramids-1999884.onnx",
+                "reward": 1.736714284334864,
+                "creation_time": 1691545991.9412746,
                 "auxillary_file_paths": [
-                    "results/Pyramids-01/Pyramids/Pyramids-999949.pt"
+                    "results/Pyramids-02/Pyramids/Pyramids-1999884.pt"
                 ]
             },
             {
-                "steps": 1000077,
-                "file_path": "results/Pyramids-01/Pyramids/Pyramids-1000077.onnx",
-                "reward": 1.8086666415135066,
-                "creation_time": 1691539693.40762,
+                "steps": 2499989,
+                "file_path": "results/Pyramids-02/Pyramids/Pyramids-2499989.onnx",
+                "reward": 1.8374999836087227,
+                "creation_time": 1691546422.788509,
                 "auxillary_file_paths": [
-                    "results/Pyramids-01/Pyramids/Pyramids-1000077.pt"
+                    "results/Pyramids-02/Pyramids/Pyramids-2499989.pt"
+                ]
+            },
+            {
+                "steps": 2999902,
+                "file_path": "results/Pyramids-02/Pyramids/Pyramids-2999902.onnx",
+                "reward": null,
+                "creation_time": 1691546847.7343323,
+                "auxillary_file_paths": [
+                    "results/Pyramids-02/Pyramids/Pyramids-2999902.pt"
+                ]
+            },
+            {
+                "steps": 3000030,
+                "file_path": "results/Pyramids-02/Pyramids/Pyramids-3000030.onnx",
+                "reward": null,
+                "creation_time": 1691546847.7867718,
+                "auxillary_file_paths": [
+                    "results/Pyramids-02/Pyramids/Pyramids-3000030.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000077,
-            "file_path": "results/Pyramids-01/Pyramids.onnx",
-            "reward": 1.8086666415135066,
-            "creation_time": 1691539693.40762,
+            "steps": 3000030,
+            "file_path": "results/Pyramids-02/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1691546847.7867718,
             "auxillary_file_paths": [
-                "results/Pyramids-01/Pyramids/Pyramids-1000077.pt"
+                "results/Pyramids-02/Pyramids/Pyramids-3000030.pt"
             ]
         }
     },