Attempt2

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1e1fffdceb466face92cbe366d64a85094217c78e97ff1dd77c6c6d96cfd2c
-size 646532
+oid sha256:7e8ac4c2cdef9a859e97da6a396fc7f43f5f4721549ffc9817d46446e261543f
+size 326963

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a5435c447311075879c2d1a36651053369af3a962db23faf5b11b18d4776851
-size 646532
+oid sha256:cd21b971b6334bfb2273d3cb4954514aecc25f7fd891872a8440dc1563db327e
+size 326963

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a102800bfc9c386900c79d64bd6bb7f8f03bb367f4dfc7ebf4333da214878951
-size 3843968
+oid sha256:d6d400bc8f4c6a99624402e0cebdb8ae8243d1b650a4f390fbaeb672caf6bbbb
+size 1938524

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde3586498c099a49193ee80f54c93260a7309e3a14d241cc9677f77591a849c
-size 646532
+oid sha256:2e04099a3b1bec183694255fae0957297da26921dd6deb76ab87746ea3e4e10f
+size 326963

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d87bd88f8c97fbe7b2fbddd00d5117a9db641bd0f7241f150d9770fd543ff854
-size 3843968
+oid sha256:73cd14430ad13e8723c8f78753451f1be96698f2188d36f4b42e358653cd09bd
+size 1938524

SnowballTarget/SnowballTarget-249944.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e01cd74e4bf35d9b45e06f79a0461d19d95427e0cd471bedbafbbeb023fdff77
-size 646532
+oid sha256:f906cf747a64f5943fb0e268ef70285ded3e779a306dd81d43184eaf0112d16f
+size 326963

SnowballTarget/SnowballTarget-249944.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa311a6b26572add11ca9f9a3846ed22e03680ab0a69bcf2679ff0735795ddfd
-size 3843968
+oid sha256:8894381fbf40036babb3be65d261043031bab3368c6bcf68a6d47684287a6222
+size 1938524

SnowballTarget/SnowballTarget-299968.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39db50fd6cf3f943e02c9b6065906822365ea8a644a1f9be03754529c84bc724
-size 646532
+oid sha256:3cb54d5914865095eecdc5256c1277de926f025cf8e54ab2aef0986b1e916e67
+size 326963

SnowballTarget/SnowballTarget-299968.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd166fc81b42c7b6718c74aa07f5e502a968b36fd08a1b216e7683d8b750ff9a
-size 3843968
+oid sha256:7f7da96fea0ddb3234d3b3f6252d134c451d4d2b989ade5111215efe63f18dab
+size 1938524

SnowballTarget/SnowballTarget-349992.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919321b0064638441316b6a9153ab3d8b4371750b750826aa261dd554ba89d83
-size 646532
+oid sha256:82e8942d043ba3366372aed418d0a4e7fb5c38723d5ac612c70b5f33436d34f5
+size 326963

SnowballTarget/SnowballTarget-349992.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ea77bbc6d0950a28f9e4fe804b7bcfd3c137be4997bddd958c057bf0456cfd
-size 3843968
+oid sha256:0e0a6a8f22bc0a2d78aeb29cbb58d5f6e1745fe569199a5243f7167a68550c03
+size 1938524

SnowballTarget/SnowballTarget-399992.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c4fdf00951ac071db7791a42ef2e8f8c95cfa35202fdcf09ade05a71756781
-size 646532
+oid sha256:ac2f8795efba0fd5e8915af6deb22f34a4500c321b37add4fe9b4deb04adebf5
+size 326963

SnowballTarget/SnowballTarget-399992.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5f7fa2fedeed869c41c56fd0c4a9ddbb31dc6597a6a20fb39efd78f739a0b53
-size 3843968
+oid sha256:79f86ef45f763c30754045d71a2cdd3d9ddc88acf5536e671ca943b6c3a493f0
+size 1938524

SnowballTarget/SnowballTarget-449952.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db68880e823a5466170aa86807ceff2614b61c9e2328a4e707cb753d1310d7fb
-size 646532
+oid sha256:68b84f2960eb384159534fb0308c4c36f0c3826480ebcb53c5453b573722d2ef
+size 326963

SnowballTarget/SnowballTarget-449952.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a73f580aaea7e27fed34dfbf982ef933d32d0a502bb1178a5e6d890558cb0c
-size 3843968
+oid sha256:f71a38e4dbdc33ec62b6a03dd0aa20059ab511238fc7bd1b9bb704243b6ca6ab
+size 1938524

SnowballTarget/SnowballTarget-499976.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1e1fffdceb466face92cbe366d64a85094217c78e97ff1dd77c6c6d96cfd2c
-size 646532
+oid sha256:7e8ac4c2cdef9a859e97da6a396fc7f43f5f4721549ffc9817d46446e261543f
+size 326963

SnowballTarget/SnowballTarget-499976.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a717657ad40f64d1563acf12e29b42fbe96165e66c67d8eca5823c099bb71a
-size 3843968
+oid sha256:afe648e6d1f5a43d3c8557778e1e88bbf5c1b852cba330293b1577f37d572901
+size 1938524

SnowballTarget/SnowballTarget-500104.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1e1fffdceb466face92cbe366d64a85094217c78e97ff1dd77c6c6d96cfd2c
-size 646532
+oid sha256:7e8ac4c2cdef9a859e97da6a396fc7f43f5f4721549ffc9817d46446e261543f
+size 326963

SnowballTarget/SnowballTarget-500104.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44a3cb9ab7ff29d9392e5df1a416eea411d1668d54159095bbd91ad0ea45f56a
-size 3843968
+oid sha256:97a13406d3b0801c22752ae24da1e21e324945a4b5bbdbd81213d740aabc2f83
+size 1938524

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:192510f4c007aea22cd111156c8dfaf98e72a9b6a591699b0c39ad5f48acdfe5
-size 646532
+oid sha256:f1a1dd8c84f9e4996c2d3c9e1afd764c74a9ffc975c71afce20dd45da57764f9
+size 326963

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c37573de96f50298603c6573eb070bec5afd49a6ab67d14831e6180136ce55d8
-size 3843968
+oid sha256:106b5e721f18a2387a0224a15d4369dbe373b1d20b0e0da5e457d47ef59eede2
+size 1938524

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44a3cb9ab7ff29d9392e5df1a416eea411d1668d54159095bbd91ad0ea45f56a
-size 3843968
+oid sha256:97a13406d3b0801c22752ae24da1e21e324945a4b5bbdbd81213d740aabc2f83
+size 1938524

SnowballTarget/{events.out.tfevents.1680429058.aa5e923e6146.7781.0 → events.out.tfevents.1680431052.aa5e923e6146.16497.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4877c85f3dccd17a261d8a6ddf2125a41489da8f988dd0623ddea02feb131f
-size 48249
+oid sha256:2c20083069b402466b27be094ccd8a244c074527467ee517ef2d2426f50c0697
+size 52586

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "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": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.001, "beta": 0.007, "epsilon": 0.2, "lambd": 0.96, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 3, "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}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,10 +5,10 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0003
-      beta: 0.005
+      learning_rate: 0.001
+      beta: 0.007
       epsilon: 0.2
-      lambd: 0.95
+      lambd: 0.96
       num_epoch: 3
       shared_critic: false
       learning_rate_schedule: linear
@@ -17,8 +17,8 @@ behaviors:
     checkpoint_interval: 50000
     network_settings:
       normalize: false
-      hidden_units: 256
-      num_layers: 2
+      hidden_units: 128
+      num_layers: 3
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.081 seconds
+- Completed reload, in  0.080 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +42,7 @@ 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: 0.735158 ms
+UnloadTime: 0.618109 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -50,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 13425 frames, [16.0 KB-32.0 KB]: 227 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 13416 frames, [16.0 KB-32.0 KB]: 227 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
@@ -166,22 +166,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 44
+  Peak main deferred allocation count 45
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 11159 frames, [8.0 MB-16.0 MB]: 2494 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 11110 frames, [8.0 MB-16.0 MB]: 2534 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 9.7 MB
+      Peak Allocated memory 9.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 13653 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13644 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 17.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -210,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 12485 frames, [64.0 KB-128.0 KB]: 1168 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13038 frames, [64.0 KB-128.0 KB]: 606 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 13653 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13644 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 13653 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13644 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 13652 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13643 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -246,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 13653 frames
+      Peak usage frame count: [0-1.0 KB]: 13644 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]: 13653 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 13644 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.7794438004493713,
-            "min": 0.769217848777771,
-            "max": 2.8614861965179443,
+            "value": 0.9076099991798401,
+            "min": 0.9076099991798401,
+            "max": 2.8623406887054443,
             "count": 50
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 7605.033203125,
-            "min": 7520.01171875,
-            "max": 29367.43359375,
+            "value": 8785.6650390625,
+            "min": 8785.6650390625,
+            "max": 29344.716796875,
             "count": 50
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 50
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.735799789428711,
-            "min": 0.1711287796497345,
-            "max": 13.90906047821045,
+            "value": 14.108038902282715,
+            "min": 0.5381110310554504,
+            "max": 14.108038902282715,
             "count": 50
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2815.8388671875,
-            "min": 33.19898223876953,
-            "max": 2842.3603515625,
+            "value": 2892.14794921875,
+            "min": 104.39353942871094,
+            "max": 2892.14794921875,
             "count": 50
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,39 +50,39 @@
             "count": 50
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07091386185683066,
-            "min": 0.06160780617602879,
-            "max": 0.0754181212882566,
+            "value": 0.07024131641887565,
+            "min": 0.05859752080954529,
+            "max": 0.0768773556619691,
             "count": 50
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.35456930928415326,
-            "min": 0.24643122470411516,
-            "max": 0.377090606441283,
+            "value": 0.3512065820943783,
+            "min": 0.23439008323818117,
+            "max": 0.36810750479078563,
             "count": 50
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.17666345916542353,
-            "min": 0.09802576110757633,
-            "max": 0.2818825277043324,
+            "value": 0.185192534327507,
+            "min": 0.14188875462038114,
+            "max": 0.3432107374218164,
             "count": 50
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8833172958271176,
-            "min": 0.3921030444303053,
-            "max": 1.244458389925022,
+            "value": 0.9259626716375351,
+            "min": 0.5675550184815246,
+            "max": 1.6073153565327325,
             "count": 50
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 3.0528989824000028e-06,
-            "min": 3.0528989824000028e-06,
-            "max": 0.00029675280108239997,
+            "value": 1.0176098982400003e-05,
+            "min": 1.0176098982400003e-05,
+            "max": 0.0009891760010824,
             "count": 50
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 1.5264494912000015e-05,
-            "min": 1.5264494912000015e-05,
-            "max": 0.001454064015312,
+            "value": 5.088049491200002e-05,
+            "min": 5.088049491200002e-05,
+            "max": 0.0048468800153119995,
             "count": 50
         },
         "SnowballTarget.Policy.Epsilon.mean": {
@@ -98,39 +98,39 @@
             "count": 50
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 6.0778240000000044e-05,
-            "min": 6.0778240000000044e-05,
-            "max": 0.00494598824,
+            "value": 8.113024000000005e-05,
+            "min": 8.113024000000005e-05,
+            "max": 0.00692434024,
             "count": 50
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0003038912000000002,
-            "min": 0.0003038912000000002,
-            "max": 0.0242359312,
+            "value": 0.00040565120000000027,
+            "min": 0.00040565120000000027,
+            "max": 0.0339296912,
             "count": 50
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 27.01818181818182,
-            "min": 2.9318181818181817,
-            "max": 27.40740740740741,
+            "value": 27.618181818181817,
+            "min": 3.8181818181818183,
+            "max": 27.98181818181818,
             "count": 50
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1486.0,
-            "min": 129.0,
-            "max": 1497.0,
+            "value": 1519.0,
+            "min": 168.0,
+            "max": 1539.0,
             "count": 50
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 27.01818181818182,
-            "min": 2.9318181818181817,
-            "max": 27.40740740740741,
+            "value": 27.618181818181817,
+            "min": 3.8181818181818183,
+            "max": 27.98181818181818,
             "count": 50
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1486.0,
-            "min": 129.0,
-            "max": 1497.0,
+            "value": 1519.0,
+            "min": 168.0,
+            "max": 1539.0,
             "count": 50
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,7 +148,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1680429058",
+        "start_time_seconds": "1680431052",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
@@ -156,59 +156,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1680430214"
+        "end_time_seconds": "1680432199"
     },
-    "total": 1155.816538462,
+    "total": 1147.5846234949995,
     "count": 1,
-    "self": 0.7799762839999858,
+    "self": 0.3831024679989241,
     "children": {
         "run_training.setup": {
-            "total": 0.10557375099983801,
+            "total": 0.10527087800028312,
             "count": 1,
-            "self": 0.10557375099983801
+            "self": 0.10527087800028312
         },
         "TrainerController.start_learning": {
-            "total": 1154.930988427,
+            "total": 1147.0962501490003,
             "count": 1,
-            "self": 1.35956119197499,
+            "self": 1.3202531629540317,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.268539559999908,
+                    "total": 3.4788207030001104,
                     "count": 1,
-                    "self": 4.268539559999908
+                    "self": 3.4788207030001104
                 },
                 "TrainerController.advance": {
-                    "total": 1149.0903089550254,
-                    "count": 45507,
-                    "self": 0.6911831659599557,
+                    "total": 1142.1677606410462,
+                    "count": 45477,
+                    "self": 0.6545610391285663,
                     "children": {
                         "env_step": {
-                            "total": 1148.3991257890655,
-                            "count": 45507,
-                            "self": 838.9038802160485,
+                            "total": 1141.5131996019177,
+                            "count": 45477,
+                            "self": 831.4854457857655,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 308.7796133849972,
-                                    "count": 45507,
-                                    "self": 4.300721927978202,
+                                    "total": 309.3698402861228,
+                                    "count": 45477,
+                                    "self": 4.258624800032521,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 304.478891457019,
-                                            "count": 45507,
-                                            "self": 304.478891457019
+                                            "total": 305.11121548609026,
+                                            "count": 45477,
+                                            "self": 305.11121548609026
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7156321880197538,
-                                    "count": 45507,
+                                    "total": 0.6579135300294183,
+                                    "count": 45477,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1151.229387694056,
-                                            "count": 45507,
+                                            "total": 1143.2282684159159,
+                                            "count": 45477,
                                             "is_parallel": true,
-                                            "self": 527.9214686660557,
+                                            "self": 532.258437057948,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0019385410000722914,
+                                                            "total": 0.001822249999804626,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006229280002116866,
+                                                            "self": 0.0005693119987881801,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013156129998606048,
+                                                                    "total": 0.001252938001016446,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013156129998606048
+                                                                    "self": 0.001252938001016446
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.11472348799998144,
+                                                            "total": 0.047262445999876945,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008184110001820954,
+                                                            "self": 0.0003612219989008736,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00043315900006746233,
+                                                                    "total": 0.00031873800026005483,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00043315900006746233
+                                                                    "self": 0.00031873800026005483
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.1096483259998422,
+                                                                    "total": 0.045516626000335236,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.1096483259998422
+                                                                    "self": 0.045516626000335236
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.003823591999889686,
+                                                                    "total": 0.0010658600003807805,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005145469997387409,
+                                                                    "self": 0.00023944299937284086,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0033090450001509453,
+                                                                            "total": 0.0008264170010079397,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0033090450001509453
+                                                                            "self": 0.0008264170010079397
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 623.3079190280002,
-                                                    "count": 45506,
+                                                    "total": 610.9698313579679,
+                                                    "count": 45476,
                                                     "is_parallel": true,
-                                                    "self": 24.74701056787626,
+                                                    "self": 24.534858940867252,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 14.338586199028668,
-                                                            "count": 45506,
+                                                            "total": 13.40537451399996,
+                                                            "count": 45476,
                                                             "is_parallel": true,
-                                                            "self": 14.338586199028668
+                                                            "self": 13.40537451399996
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 502.19646343604745,
-                                                            "count": 45506,
+                                                            "total": 492.1718367020362,
+                                                            "count": 45476,
                                                             "is_parallel": true,
-                                                            "self": 502.19646343604745
+                                                            "self": 492.1718367020362
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 82.02585882504786,
-                                                            "count": 45506,
+                                                            "total": 80.85776120106448,
+                                                            "count": 45476,
                                                             "is_parallel": true,
-                                                            "self": 16.147291615917993,
+                                                            "self": 15.987068659212127,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 65.87856720912987,
-                                                                    "count": 455060,
+                                                                    "total": 64.87069254185235,
+                                                                    "count": 454760,
                                                                     "is_parallel": true,
-                                                                    "self": 65.87856720912987
+                                                                    "self": 64.87069254185235
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00011846999996123486,
+                    "total": 0.00011574400014069397,
                     "count": 1,
-                    "self": 0.00011846999996123486,
+                    "self": 0.00011574400014069397,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 1140.0188054531313,
-                                    "count": 1042290,
+                                    "total": 1133.4342856535195,
+                                    "count": 1034286,
                                     "is_parallel": true,
-                                    "self": 25.206867358745285,
+                                    "self": 25.187041478791798,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 631.6825475373869,
-                                            "count": 1042290,
+                                            "total": 627.3703568027217,
+                                            "count": 1034286,
                                             "is_parallel": true,
-                                            "self": 628.1209678053867,
+                                            "self": 624.8085960577223,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 3.5615797320001548,
+                                                    "total": 2.5617607449994466,
                                                     "count": 10,
                                                     "is_parallel": true,
-                                                    "self": 3.5615797320001548
+                                                    "self": 2.5617607449994466
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 483.12939055699917,
+                                            "total": 480.87688737200597,
                                             "count": 227,
                                             "is_parallel": true,
-                                            "self": 178.141558771998,
+                                            "self": 172.03355409504002,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 304.98783178500116,
+                                                    "total": 308.84333327696595,
                                                     "count": 11574,
                                                     "is_parallel": true,
-                                                    "self": 304.98783178500116
+                                                    "self": 308.84333327696595
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.21246024999982183,
+                    "total": 0.12929989799977193,
                     "count": 1,
-                    "self": 0.002099129999805882,
+                    "self": 0.000816151999970316,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.21036112000001594,
+                            "total": 0.1284837459998016,
                             "count": 1,
-                            "self": 0.21036112000001594
+                            "self": 0.1284837459998016
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 21.727272727272727,
-                "creation_time": 1680429296.4610813,
+                "reward": 22.0,
+                "creation_time": 1680431286.9806924,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 25.0,
-                "creation_time": 1680429412.1024163,
+                "reward": 25.454545454545453,
+                "creation_time": 1680431402.9457452,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.90909090909091,
-                "creation_time": 1680429525.4227335,
+                "reward": 26.454545454545453,
+                "creation_time": 1680431518.3806846,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 249944,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
-                "reward": 26.454545454545453,
-                "creation_time": 1680429639.5173824,
+                "reward": 25.90909090909091,
+                "creation_time": 1680431634.4951496,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
                 ]
@@ -40,8 +40,8 @@
             {
                 "steps": 299968,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
-                "reward": 27.272727272727273,
-                "creation_time": 1680429754.9410768,
+                "reward": 25.181818181818183,
+                "creation_time": 1680431749.2137773,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
                 ]
@@ -49,8 +49,8 @@
             {
                 "steps": 349992,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
-                "reward": 27.363636363636363,
-                "creation_time": 1680429869.1451,
+                "reward": 27.636363636363637,
+                "creation_time": 1680431862.7742105,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
                 ]
@@ -58,8 +58,8 @@
             {
                 "steps": 399992,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
-                "reward": 26.818181818181817,
-                "creation_time": 1680429982.9439065,
+                "reward": 27.272727272727273,
+                "creation_time": 1680431974.3715184,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
                 ]
@@ -68,7 +68,7 @@
                 "steps": 449952,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
                 "reward": 27.181818181818183,
-                "creation_time": 1680430097.4575415,
+                "creation_time": 1680432087.5055535,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
                 ]
@@ -76,8 +76,8 @@
             {
                 "steps": 499976,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
-                "reward": 27.363636363636363,
-                "creation_time": 1680430213.0998704,
+                "reward": 26.545454545454547,
+                "creation_time": 1680432199.3106952,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
                 ]
@@ -85,8 +85,8 @@
             {
                 "steps": 500104,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
-                "reward": 27.363636363636363,
-                "creation_time": 1680430213.3303428,
+                "reward": 26.545454545454547,
+                "creation_time": 1680432199.4643004,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
                 ]
@@ -95,8 +95,8 @@
         "final_checkpoint": {
             "steps": 500104,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 27.363636363636363,
-            "creation_time": 1680430213.3303428,
+            "reward": 26.545454545454547,
+            "creation_time": 1680432199.4643004,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
             ]