Second Huggy model

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6bc63848c305f0ac53d1fb9213b814567412506a37bbdfe8f0046cf8f9cea1
+oid sha256:7bbb3e5654668ec226c366695c1294110481ef1ede0e873b8d509793e7bfe55a
 size 2274020

Huggy/Huggy-1199884.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453e38b4fffbec9b3b1e979001b618e73d14c80498e7c04882e8c12350b35331
+size 2274020

Huggy/Huggy-1199884.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7c91cb6d0f36e29b2e8434ee5202c2a2683bc708a50f3f5de961efc12f82f6
+size 13509236

Huggy/Huggy-1399949.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1935384b4f2fca649989d51e3cca39d165d84132ce0284b717df689bbd7b69a
+size 2274020

Huggy/Huggy-1399949.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10d286c6b3efda3e1a549b059a3f368087c8fda8f6706226254c4cfd17f1b23
+size 13509236

Huggy/Huggy-1599853.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33c61b7ddb492c745a3cf8d7ce0498986d9715ef73a610cbe27d81a8e6501ea
+size 2274020

Huggy/Huggy-1599853.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6b3cb7bccbe91040671e5d7f44127c46638f248fd258037604dbe9fdecd286
+size 13509236

Huggy/Huggy-1799950.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d834ec0d89309fe8a5fb750bab40fe1585e2c4e72d60ac20e8a86b8d0fb2c7
+size 2274020

Huggy/Huggy-1799950.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92b54f3c3d7383deec98b1b9395679df9e2b5120dfd75cd19758908a5ee4d76
+size 13509236

Huggy/Huggy-199427.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88843c52f4ba5196c91a59e1a7156a8c642fbb229c9dd8db14caa7321a00e612
+size 2274020

Huggy/Huggy-199427.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00da18e08ca7da4e10da488c5bc490b9aa81dc9fc6a59b7de4068bf5d76e61a5
+size 13509151

Huggy/Huggy-1999637.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7173c21ad62d4840d608808ae530ca2250b58d2b971c128f7e4e423725c6c4
+size 2274020

Huggy/Huggy-1999637.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fdaabc5e22ba292e1105f1ebc40129d8ce823211496bb68228be79fe95d88d
+size 13509236

Huggy/Huggy-2000387.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbb3e5654668ec226c366695c1294110481ef1ede0e873b8d509793e7bfe55a
+size 2274020

Huggy/Huggy-2000387.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0564d8d1b8f2d9cf5f9947b43839a3361d48af772ba0a99a37917f4e4b4bef13
+size 13509236

Huggy/Huggy-399765.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6a5ba1a2e52050e1ac889821da3492eb1c3bb90e78dd646cffb7ec62acffff
+size 2274020

Huggy/Huggy-399765.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e951116bfd511ebfa588c054dbde4c57ba0499b42082fcf53d2e15e2485f083
+size 13509151

Huggy/Huggy-599889.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26d8586955e26a41fff4c5c62e38d0aeccd580eea9c1f5e7941c0d903dddb07
+size 2274020

Huggy/Huggy-599889.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e4b55d1258293ec182092ec0c08e9f5ea54e81f3611c0c05d3aa7cc022e303
+size 13509151

Huggy/Huggy-799944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41ce3b2e26bca7141279db200d626d3a4c9cb0fd3877e0af03a026c61ca80b0
+size 2274020

Huggy/Huggy-799944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842796d1c52b390667fb72541b478633219154403fa7bd97294252d1183af3b1
+size 13509151

Huggy/Huggy-999874.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7bd8c6e6ce02f8599297f8fca3ff5ec48050d94d5f57df0aeb2ff3242a985a7
+size 2274020

Huggy/Huggy-999874.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec9e7771341c67a89c5aeb481503c2b27f040b0dc829b1c7235c6c323226645
+size 13509151

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f083851052713d42a854c3f8f4279feaf40d7bb6c58a885e170e7c73821b09
+oid sha256:418666416b17d5eb6337708e107e34932bbe4062e315372e0ef38a4e24502179
 size 13508981

Huggy/events.out.tfevents.1768424040.fedora.24386.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb5f6ab52c61ca2b46e1d6e7d16a2a2fd9ccb4e765a661b552ee28f0ba993dd
+size 340113

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy2", "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": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.98, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.999, "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}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy3", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,10 +5,10 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.0003
+      learning_rate: 0.0005
       beta: 0.005
       epsilon: 0.2
-      lambd: 0.95
+      lambd: 0.98
       num_epoch: 3
       shared_critic: false
       learning_rate_schedule: linear
@@ -25,7 +25,7 @@ behaviors:
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.995
+        gamma: 0.999
         strength: 1.0
         network_settings:
           normalize: false
@@ -66,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Huggy2
+  run_id: Huggy3
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/home/kaneki/Documenti/DeepRLCourse/unit1/trained-envs-executabl
 Mono config path = '/home/kaneki/Documenti/DeepRLCourse/unit1/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /home/kaneki/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /home/kaneki/.config/unity3d/Hugging Face/Huggy
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /home/kaneki/Documenti/DeepRLCourse/unit1/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -14,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.071 seconds
+- Completed reload, in  0.059 seconds
 ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -58,14 +55,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
 WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - 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: 0.525160 ms
+UnloadTime: 0.592670 ms
 requesting resize 84 x 84
 Setting up 6 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [4.0 KB-8.0 KB]: 26755 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26753 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 3.6 MB
@@ -231,22 +228,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 53
+  Peak main deferred allocation count 38
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 26756 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26754 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.7 MB
+      Peak Allocated memory 23.2 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26756 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 26754 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 2.6 MB
+      Peak Allocated memory 2.5 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -275,13 +272,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 26755 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26753 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 26756 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 26754 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -293,13 +290,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 26755 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26753 frames, [16.0 MB-32.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 24.9 MB
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 26755 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 26753 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.6 MB
@@ -311,13 +308,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26756 frames
+      Peak usage frame count: [0-1.0 KB]: 26754 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: [4.0 KB-8.0 KB]: 26756 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26754 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -2,135 +2,135 @@
     "name": "root",
     "gauges": {
         "Huggy.Policy.Entropy.mean": {
-            "value": 1.4053866863250732,
-            "min": 1.4053866863250732,
-            "max": 1.4271067380905151,
+            "value": 1.391542673110962,
+            "min": 1.3915420770645142,
+            "max": 1.4233204126358032,
             "count": 40
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": 68700.921875,
-            "min": 68333.0,
-            "max": 75852.03125,
+            "value": 72312.90625,
+            "min": 66933.171875,
+            "max": 77407.515625,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 98.3913043478261,
-            "min": 85.80521739130435,
-            "max": 405.7317073170732,
+            "value": 124.64837905236908,
+            "min": 114.6674364896074,
+            "max": 415.3223140495868,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 49786.0,
-            "min": 49096.0,
-            "max": 50166.0,
+            "value": 49984.0,
+            "min": 48899.0,
+            "max": 50264.0,
             "count": 40
         },
         "Huggy.Step.mean": {
-            "value": 1999635.0,
-            "min": 49278.0,
-            "max": 1999635.0,
+            "value": 1999637.0,
+            "min": 49942.0,
+            "max": 1999637.0,
             "count": 40
         },
         "Huggy.Step.sum": {
-            "value": 1999635.0,
-            "min": 49278.0,
-            "max": 1999635.0,
+            "value": 1999637.0,
+            "min": 49942.0,
+            "max": 1999637.0,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.4080748558044434,
-            "min": 0.0414591059088707,
-            "max": 2.447978973388672,
+            "value": 2.3118081092834473,
+            "min": 0.1199059784412384,
+            "max": 2.569995403289795,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1218.48583984375,
-            "min": 5.058011054992676,
-            "max": 1401.1405029296875,
+            "value": 927.0350341796875,
+            "min": 14.388717651367188,
+            "max": 1107.66796875,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.7214938744961508,
-            "min": 1.8799241792227401,
-            "max": 3.953162371290141,
+            "value": 3.386072400650776,
+            "min": 1.9037643402814866,
+            "max": 3.8050859271758406,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": 1883.0759004950523,
-            "min": 229.3507498651743,
-            "max": 2218.2683618068695,
+            "value": 1357.8150326609612,
+            "min": 228.45172083377838,
+            "max": 1611.8025605082512,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.7214938744961508,
-            "min": 1.8799241792227401,
-            "max": 3.953162371290141,
+            "value": 3.386072400650776,
+            "min": 1.9037643402814866,
+            "max": 3.8050859271758406,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 1883.0759004950523,
-            "min": 229.3507498651743,
-            "max": 2218.2683618068695,
+            "value": 1357.8150326609612,
+            "min": 228.45172083377838,
+            "max": 1611.8025605082512,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.01699627729554373,
-            "min": 0.013862839164923773,
-            "max": 0.019315852512954736,
+            "value": 0.01775079543922402,
+            "min": 0.013714471299075133,
+            "max": 0.021381704290009414,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.050988831886631183,
-            "min": 0.027901822801989815,
-            "max": 0.0566010097124187,
+            "value": 0.03550159087844804,
+            "min": 0.027428942598150267,
+            "max": 0.05760770578441831,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.052767536085512906,
-            "min": 0.02220022932936748,
-            "max": 0.05993017914394537,
+            "value": 0.0726849070439736,
+            "min": 0.0335767546047767,
+            "max": 0.07794048264622688,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.15830260825653872,
-            "min": 0.04440045865873496,
-            "max": 0.17863047358890374,
+            "value": 0.1453698140879472,
+            "min": 0.0671535092095534,
+            "max": 0.23382144793868065,
             "count": 40
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 3.5344988218666706e-06,
-            "min": 3.5344988218666706e-06,
-            "max": 0.00029534175155275006,
+            "value": 7.723973455224988e-06,
+            "min": 7.723973455224988e-06,
+            "max": 0.0004921158765768251,
             "count": 40
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 1.0603496465600011e-05,
-            "min": 1.0603496465600011e-05,
-            "max": 0.0008439042186986,
+            "value": 1.5447946910449976e-05,
+            "min": 1.5447946910449976e-05,
+            "max": 0.0014062875187425,
             "count": 40
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.10117813333333335,
-            "min": 0.10117813333333335,
-            "max": 0.19844725000000002,
+            "value": 0.101544775,
+            "min": 0.101544775,
+            "max": 0.198423175,
             "count": 40
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.30353440000000004,
-            "min": 0.20748260000000002,
-            "max": 0.5813013999999999,
+            "value": 0.20308955,
+            "min": 0.20308955,
+            "max": 0.5812575000000001,
             "count": 40
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 6.878885333333342e-05,
-            "min": 6.878885333333342e-05,
-            "max": 0.0049225177749999995,
+            "value": 8.708427249999991e-05,
+            "min": 8.708427249999991e-05,
+            "max": 0.004921316432500001,
             "count": 40
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.00020636656000000027,
-            "min": 0.00020636656000000027,
-            "max": 0.01406693986,
+            "value": 0.00017416854499999982,
+            "min": 0.00017416854499999982,
+            "max": 0.014064749249999996,
             "count": 40
         },
         "Huggy.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1768421842",
+        "start_time_seconds": "1768424039",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/home/kaneki/miniconda3/envs/deepRL2/bin/mlagents-learn ./ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
+        "command_line_arguments": "/home/kaneki/miniconda3/envs/deepRL2/bin/mlagents-learn ./ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy3 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1768422899"
+        "end_time_seconds": "1768425072"
     },
-    "total": 1057.1222388170008,
+    "total": 1033.1432527799989,
     "count": 1,
-    "self": 0.21792120600002818,
+    "self": 0.21874462899904756,
     "children": {
         "run_training.setup": {
-            "total": 0.01761234500008868,
+            "total": 0.018344996999076102,
             "count": 1,
-            "self": 0.01761234500008868
+            "self": 0.018344996999076102
         },
         "TrainerController.start_learning": {
-            "total": 1056.8867052660007,
+            "total": 1032.9061631540008,
             "count": 1,
-            "self": 1.9394072989580309,
+            "self": 1.9261722780902346,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.6396101089994772,
+                    "total": 1.6203490660009265,
                     "count": 1,
-                    "self": 1.6396101089994772
+                    "self": 1.6203490660009265
                 },
                 "TrainerController.advance": {
-                    "total": 1053.2234103380415,
-                    "count": 232002,
-                    "self": 2.03021419392644,
+                    "total": 1029.2912804179105,
+                    "count": 229668,
+                    "self": 2.0401697566067014,
                     "children": {
                         "env_step": {
-                            "total": 805.7738243299918,
-                            "count": 232002,
-                            "self": 588.6176870253348,
+                            "total": 792.3017616174075,
+                            "count": 229668,
+                            "self": 575.0523976776713,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 215.8246528255604,
-                                    "count": 232002,
-                                    "self": 6.999051692153444,
+                                    "total": 215.89413844461524,
+                                    "count": 229668,
+                                    "self": 6.778385376683218,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 208.82560113340696,
-                                            "count": 222964,
-                                            "self": 208.82560113340696
+                                            "total": 209.11575306793202,
+                                            "count": 222948,
+                                            "self": 209.11575306793202
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.3314844790966163,
-                                    "count": 232002,
+                                    "total": 1.3552254951209761,
+                                    "count": 229668,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1053.7121616003078,
-                                            "count": 232002,
+                                            "total": 1029.85817447945,
+                                            "count": 229668,
                                             "is_parallel": true,
-                                            "self": 583.0456920454762,
+                                            "self": 570.7588859379266,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0005885289992875187,
+                                                            "total": 0.0005235690005065408,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00015488999997614883,
+                                                            "self": 0.00014258000010158867,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.00043363899931136984,
+                                                                    "total": 0.0003809890004049521,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00043363899931136984
+                                                                    "self": 0.0003809890004049521
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.014785900000788388,
+                                                            "total": 0.014328004001072259,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00012783899910573382,
+                                                            "self": 0.0001343099993391661,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00016883900025277399,
+                                                                    "total": 0.00015609000001859386,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00016883900025277399
+                                                                    "self": 0.00015609000001859386
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.01418285200088576,
+                                                                    "total": 0.013722385001528892,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.01418285200088576
+                                                                    "self": 0.013722385001528892
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.00030637000054412056,
+                                                                    "total": 0.000315219000185607,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 8.888000047591049e-05,
+                                                                    "self": 9.59999997576233e-05,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00021749000006821007,
+                                                                            "total": 0.0002192190004279837,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.00021749000006821007
+                                                                            "self": 0.0002192190004279837
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 470.66646955483156,
-                                                    "count": 232001,
+                                                    "total": 459.0992885415235,
+                                                    "count": 229667,
                                                     "is_parallel": true,
-                                                    "self": 15.640811230719919,
+                                                    "self": 15.49274085604884,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 29.662126053519387,
-                                                            "count": 232001,
+                                                            "total": 29.177503121549307,
+                                                            "count": 229667,
                                                             "is_parallel": true,
-                                                            "self": 29.662126053519387
+                                                            "self": 29.177503121549307
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 390.70390570098607,
-                                                            "count": 232001,
+                                                            "total": 380.59462096488096,
+                                                            "count": 229667,
                                                             "is_parallel": true,
-                                                            "self": 390.70390570098607
+                                                            "self": 380.59462096488096
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 34.65962656960619,
-                                                            "count": 232001,
+                                                            "total": 33.834423599044385,
+                                                            "count": 229667,
                                                             "is_parallel": true,
-                                                            "self": 13.2632972116171,
+                                                            "self": 12.85480307628859,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 21.39632935798909,
-                                                                    "count": 464002,
+                                                                    "total": 20.979620522755795,
+                                                                    "count": 459334,
                                                                     "is_parallel": true,
-                                                                    "self": 21.39632935798909
+                                                                    "self": 20.979620522755795
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 245.41937181412322,
-                            "count": 232002,
-                            "self": 3.0312018654003623,
+                            "total": 234.9493490438963,
+                            "count": 229668,
+                            "self": 2.9874360498215538,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 82.1857834647235,
-                                    "count": 232002,
-                                    "self": 81.36514876672118,
+                                    "total": 74.4728853850811,
+                                    "count": 229668,
+                                    "self": 73.57977894408032,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.8206346980023227,
+                                            "total": 0.8931064410007821,
                                             "count": 10,
-                                            "self": 0.8206346980023227
+                                            "self": 0.8931064410007821
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 160.20238648399936,
-                                    "count": 97,
-                                    "self": 130.4581682370408,
+                                    "total": 157.48902760899364,
+                                    "count": 96,
+                                    "self": 128.65103193802315,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 29.744218246958553,
-                                            "count": 2910,
-                                            "self": 29.744218246958553
+                                            "total": 28.837995670970486,
+                                            "count": 2880,
+                                            "self": 28.837995670970486
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 6.300015229498968e-07,
+                    "total": 6.099999154685065e-07,
                     "count": 1,
-                    "self": 6.300015229498968e-07
+                    "self": 6.099999154685065e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0842768900001829,
+                    "total": 0.06836078199921758,
                     "count": 1,
-                    "self": 0.0015554769997834228,
+                    "self": 0.0014345679992402438,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08272141300039948,
+                            "total": 0.06692621399997734,
                             "count": 1,
-                            "self": 0.08272141300039948
+                            "self": 0.06692621399997734
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,112 +2,112 @@
     "Huggy": {
         "checkpoints": [
             {
-                "steps": 199986,
-                "file_path": "results/Huggy2/Huggy/Huggy-199986.onnx",
-                "reward": 3.4196958440845298,
-                "creation_time": 1768421947.7026906,
+                "steps": 199427,
+                "file_path": "results/Huggy3/Huggy/Huggy-199427.onnx",
+                "reward": 3.130600761859975,
+                "creation_time": 1768424143.1313307,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-199986.pt"
+                    "results/Huggy3/Huggy/Huggy-199427.pt"
                 ]
             },
             {
-                "steps": 399965,
-                "file_path": "results/Huggy2/Huggy/Huggy-399965.onnx",
-                "reward": 3.728138251124688,
-                "creation_time": 1768422051.640638,
+                "steps": 399765,
+                "file_path": "results/Huggy3/Huggy/Huggy-399765.onnx",
+                "reward": 3.2648092661148462,
+                "creation_time": 1768424245.564162,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-399965.pt"
+                    "results/Huggy3/Huggy/Huggy-399765.pt"
                 ]
             },
             {
-                "steps": 599951,
-                "file_path": "results/Huggy2/Huggy/Huggy-599951.onnx",
-                "reward": 4.307485228776931,
-                "creation_time": 1768422157.208927,
+                "steps": 599889,
+                "file_path": "results/Huggy3/Huggy/Huggy-599889.onnx",
+                "reward": 3.3410224318504333,
+                "creation_time": 1768424347.9794557,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-599951.pt"
+                    "results/Huggy3/Huggy/Huggy-599889.pt"
                 ]
             },
             {
-                "steps": 799928,
-                "file_path": "results/Huggy2/Huggy/Huggy-799928.onnx",
-                "reward": 3.883200965212576,
-                "creation_time": 1768422261.794345,
+                "steps": 799944,
+                "file_path": "results/Huggy3/Huggy/Huggy-799944.onnx",
+                "reward": 3.6046792827876266,
+                "creation_time": 1768424449.8070247,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-799928.pt"
+                    "results/Huggy3/Huggy/Huggy-799944.pt"
                 ]
             },
             {
-                "steps": 999953,
-                "file_path": "results/Huggy2/Huggy/Huggy-999953.onnx",
-                "reward": 3.430280010215938,
-                "creation_time": 1768422367.9915109,
+                "steps": 999874,
+                "file_path": "results/Huggy3/Huggy/Huggy-999874.onnx",
+                "reward": 3.553883319430881,
+                "creation_time": 1768424553.7676537,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-999953.pt"
+                    "results/Huggy3/Huggy/Huggy-999874.pt"
                 ]
             },
             {
-                "steps": 1199350,
-                "file_path": "results/Huggy2/Huggy/Huggy-1199350.onnx",
-                "reward": 3.6494022409121194,
-                "creation_time": 1768422474.4625587,
+                "steps": 1199884,
+                "file_path": "results/Huggy3/Huggy/Huggy-1199884.onnx",
+                "reward": 3.823655982812246,
+                "creation_time": 1768424658.306003,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-1199350.pt"
+                    "results/Huggy3/Huggy/Huggy-1199884.pt"
                 ]
             },
             {
-                "steps": 1399889,
-                "file_path": "results/Huggy2/Huggy/Huggy-1399889.onnx",
-                "reward": 3.8282334490435748,
-                "creation_time": 1768422579.4924254,
+                "steps": 1399949,
+                "file_path": "results/Huggy3/Huggy/Huggy-1399949.onnx",
+                "reward": 3.9698285133318794,
+                "creation_time": 1768424760.4069405,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-1399889.pt"
+                    "results/Huggy3/Huggy/Huggy-1399949.pt"
                 ]
             },
             {
-                "steps": 1599971,
-                "file_path": "results/Huggy2/Huggy/Huggy-1599971.onnx",
-                "reward": 3.7537961048994237,
-                "creation_time": 1768422685.5177283,
+                "steps": 1599853,
+                "file_path": "results/Huggy3/Huggy/Huggy-1599853.onnx",
+                "reward": 3.701422998341181,
+                "creation_time": 1768424864.08401,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-1599971.pt"
+                    "results/Huggy3/Huggy/Huggy-1599853.pt"
                 ]
             },
             {
-                "steps": 1799956,
-                "file_path": "results/Huggy2/Huggy/Huggy-1799956.onnx",
-                "reward": 3.4614507988259033,
-                "creation_time": 1768422792.9808831,
+                "steps": 1799950,
+                "file_path": "results/Huggy3/Huggy/Huggy-1799950.onnx",
+                "reward": 3.1315163921665503,
+                "creation_time": 1768424968.89809,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-1799956.pt"
+                    "results/Huggy3/Huggy/Huggy-1799950.pt"
                 ]
             },
             {
-                "steps": 1999635,
-                "file_path": "results/Huggy2/Huggy/Huggy-1999635.onnx",
-                "reward": 3.924936047858662,
-                "creation_time": 1768422899.5090759,
+                "steps": 1999637,
+                "file_path": "results/Huggy3/Huggy/Huggy-1999637.onnx",
+                "reward": 3.2007839702210337,
+                "creation_time": 1768425072.43388,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-1999635.pt"
+                    "results/Huggy3/Huggy/Huggy-1999637.pt"
                 ]
             },
             {
-                "steps": 2000385,
-                "file_path": "results/Huggy2/Huggy/Huggy-2000385.onnx",
-                "reward": 3.7222255677790255,
-                "creation_time": 1768422899.6117468,
+                "steps": 2000387,
+                "file_path": "results/Huggy3/Huggy/Huggy-2000387.onnx",
+                "reward": 3.1617177702486514,
+                "creation_time": 1768425072.518348,
                 "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-2000385.pt"
+                    "results/Huggy3/Huggy/Huggy-2000387.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000385,
-            "file_path": "results/Huggy2/Huggy.onnx",
-            "reward": 3.7222255677790255,
-            "creation_time": 1768422899.6117468,
+            "steps": 2000387,
+            "file_path": "results/Huggy3/Huggy.onnx",
+            "reward": 3.1617177702486514,
+            "creation_time": 1768425072.518348,
             "auxillary_file_paths": [
-                "results/Huggy2/Huggy/Huggy-2000385.pt"
+                "results/Huggy3/Huggy/Huggy-2000387.pt"
             ]
         }
     },