Longer trained agent

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4077a522c941b20db55809b5914b213b0bfd25e3ddbf37cfb78b9a9168fdd2d
+oid sha256:bfd95c6aed079c6731cb9b167a427ddd6e99a4df1970b13339739f0fc36660f0
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3289b77832848b0ef7431e1a959b58c24385d5caf38a1705e43c798b95e71734
+oid sha256:8b7e2aaae342201ac33f948e7d578f706af1189f347518e171f31893cad18d4b
 size 3849883

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0adad92ba1a720e27752f59151df1978ca8478e888c945a7a02f60efd2a6f96f
+oid sha256:00a7a60000a637ecf38ff1b3b06754b1c96d92093070a43b94871fe52dbc2fb6
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:095b087dea3f26540a76a82a56376920b1412d447adb8c278b310ff888f19494
+oid sha256:543dcbeb01e6cdbaacc3efe7f08dd9a803689711812c8efdbe10b2f2e0c40a46
 size 3849883

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5495685b97e443f87c9a08922be4073d14fcbc7ae6b3a5996cc31f616ee06ba5
+size 650646

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16da0918861dd8bd9fb1603d4ef093cba0e2b4d114754d3a73918bf33b2a83e
+size 3849883

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24631fb6e3e38b64547c020a0231445ff786eecbf04f2ab2f8343bb5b4d2692e
+size 650646

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d07c7d5e2ca3474b1ab1cf36cc803f725831aefb37437aa4f96b8ca3d51233
+size 3849883

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8963dc5eb83f1f993403931f3c5bd11bbd5299b110e82bd2faf505a1714f2cee
+size 650646

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4463844144791c0a904750242955e42014919e2d8f9491ec62d4f4db20925b8c
+size 3849883

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e48fb18e000c8f6e6acfbe379364bc2d43aca7ca3017b64196e182b9be0dd7
+size 650646

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0f220337cffba1fa61336038e29892f9e37cce8e8d1b4eb24ffb5a09934c08
+size 3849883

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50a3eb5a9308338729c2e6d926975ad550f24e3042e1d54c539a969a21fb847
+size 650646

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66696a5d437264016c1702d60eddb1b7d1b9895e0dfe2c2c4783e62d20c81bdb
+size 3849883

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec42000cc02d4acc14c2cfd8dda86b1804d898acdf95a6a7fe7893cf0dab27b5
+oid sha256:728022f972a7140f93b04e047b19d7d8d1339690ce57d86606a191628acccc55
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013275b33227a973cbce214f39409b0504e2352cb7e0f9880a0fc74f23171d09
+oid sha256:6b3255fe3d8071a8a948dce6cd0b843168b3c61572e1d10a0e01ade327e5bbcc
 size 3849808

SnowballTarget/SnowballTarget-499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2328f903229b478496e8b08a0753682931b11e12583d82bdc6c8bff0ede2c16
+size 650646

SnowballTarget/SnowballTarget-499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cda30ff4a11f3b59508af6d6be56e26cb89da5f4e10e17f4366beb292f0e741
+size 3849883

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3764db3c265f7a36cbb73b45411a8221c5d2106268eb456ef01e9a725ce169b
+oid sha256:ee07749d84b637ceeb7d02cd082f7caa6fdb9458a48f6c2fe7d25f4862160199
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee2d5380cc917a3b05bd5e31470fc2422907421133feb1a124df40a0455708f
+oid sha256:94aacceefed5085aa4ed93537c28343dc04024c290889d4cb993eaf39cfc6ff6
 size 3849808

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e13aff550d61e756d95a6707d0c9cc6925d7ac85464d13aee8d5fbe1ab1a6ac
+oid sha256:cf67a98209ffa1db3d5f19aa95911d991cbf7b6cf0959f2488a73c71247a793a
 size 3849058

SnowballTarget/events.out.tfevents.1731659828.2768e6f224c9.20216.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a209758501e4dd9924d9c7fa75441603493d3f95fd5b8dae84f36c17497fce
+size 51263

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": 200000, "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, "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": "SnowballTarget2", "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": 0.0003, "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": 1000000, "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, "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": "SnowballTarget3", "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

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200000
+    max_steps: 1000000
     time_horizon: 64
     summary_freq: 10000
     threaded: true
@@ -66,11 +66,11 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget2
+  run_id: SnowballTarget3
   initialize_from: null
   load_model: false
   resume: false
-  force: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.100 seconds
+- Completed reload, in  0.090 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: 0.598904 ms
+UnloadTime: 0.711357 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]: 5368 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 14734 frames, [16.0 KB-32.0 KB]: 249 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 36
+  Peak main deferred allocation count 40
     [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]: 5460 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 10822 frames, [8.0 MB-16.0 MB]: 4162 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.6 MB
+      Peak Allocated memory 10.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 14984 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 17.6 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]: 4718 frames, [64.0 KB-128.0 KB]: 742 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 14376 frames, [64.0 KB-128.0 KB]: 608 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 66.4 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5460 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 14984 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]: 5460 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 14984 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]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 14983 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]: 5460 frames
+      Peak usage frame count: [0-1.0 KB]: 14984 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]: 5460 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 14984 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 1.0531104803085327,
-            "min": 1.0515899658203125,
-            "max": 2.864750623703003,
-            "count": 20
+            "value": 0.8140169382095337,
+            "min": 0.8097283244132996,
+            "max": 2.858764410018921,
+            "count": 54
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 10055.0986328125,
-            "min": 10055.0986328125,
-            "max": 29306.3984375,
-            "count": 20
+            "value": 8354.255859375,
+            "min": 7731.2861328125,
+            "max": 29245.16015625,
+            "count": 54
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
+            "value": 539960.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 539960.0,
+            "count": 54
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
+            "value": 539960.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 539960.0,
+            "count": 54
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.895304679870605,
-            "min": 0.3762494921684265,
-            "max": 12.895304679870605,
-            "count": 20
+            "value": 13.846375465393066,
+            "min": 0.37345069646835327,
+            "max": 13.900613784790039,
+            "count": 54
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2514.58447265625,
-            "min": 72.99240112304688,
-            "max": 2612.8486328125,
-            "count": 20
+            "value": 2824.66064453125,
+            "min": 72.44943237304688,
+            "max": 2831.68505859375,
+            "count": 54
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 54
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
+            "value": 10945.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 54
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.0748114301495929,
-            "min": 0.06069616162183629,
-            "max": 0.07670052113997586,
-            "count": 20
+            "value": 0.06835144121729422,
+            "min": 0.05989573233811968,
+            "max": 0.07579183326675311,
+            "count": 54
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2992457205983716,
-            "min": 0.25766538139706585,
-            "max": 0.364691838142736,
-            "count": 20
+            "value": 0.3417572060864711,
+            "min": 0.2395829293524787,
+            "max": 0.3735196143962265,
+            "count": 54
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1843809053374856,
-            "min": 0.14226837355447203,
-            "max": 0.2635548769989434,
-            "count": 20
+            "value": 0.16497854584572363,
+            "min": 0.1240604159059277,
+            "max": 0.28862007277853347,
+            "count": 54
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7375236213499424,
-            "min": 0.5690734942178881,
-            "max": 1.3162286325412638,
-            "count": 20
+            "value": 0.8248927292286181,
+            "min": 0.4962416636237108,
+            "max": 1.4431003638926674,
+            "count": 54
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+            "value": 0.00013964645345120003,
+            "min": 0.00013964645345120003,
+            "max": 0.0002983764005411999,
+            "count": 54
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+            "value": 0.0006982322672560001,
+            "min": 0.0005704658098448,
+            "max": 0.001477032007656,
+            "count": 54
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+            "value": 0.14654880000000003,
+            "min": 0.14654880000000003,
+            "max": 0.1994588,
+            "count": 54
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+            "value": 0.7327440000000002,
+            "min": 0.5901552000000001,
+            "max": 0.992344,
+            "count": 54
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+            "value": 0.00233278512,
+            "min": 0.00233278512,
+            "max": 0.00497299412,
+            "count": 54
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+            "value": 0.0116639256,
+            "min": 0.00952874448,
+            "max": 0.0246179656,
+            "count": 54
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.90909090909091,
-            "min": 3.8181818181818183,
-            "max": 25.836363636363636,
-            "count": 20
+            "value": 27.29090909090909,
+            "min": 3.7954545454545454,
+            "max": 27.613636363636363,
+            "count": 54
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1096.0,
-            "min": 168.0,
-            "max": 1421.0,
-            "count": 20
+            "value": 1501.0,
+            "min": 167.0,
+            "max": 1507.0,
+            "count": 54
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.90909090909091,
-            "min": 3.8181818181818183,
-            "max": 25.836363636363636,
-            "count": 20
+            "value": 27.29090909090909,
+            "min": 3.7954545454545454,
+            "max": 27.613636363636363,
+            "count": 54
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1096.0,
-            "min": 168.0,
-            "max": 1421.0,
-            "count": 20
+            "value": 1501.0,
+            "min": 167.0,
+            "max": 1507.0,
+            "count": 54
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 54
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 54
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1731658729",
+        "start_time_seconds": "1731659827",
         "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics --force",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget3.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1731659178"
+        "end_time_seconds": "1731661039"
     },
-    "total": 449.0562200210002,
+    "total": 1211.559063652,
     "count": 1,
-    "self": 0.39342205999992075,
+    "self": 0.5863407859997096,
     "children": {
         "run_training.setup": {
-            "total": 0.055959089000225504,
+            "total": 0.05506386800061591,
             "count": 1,
-            "self": 0.055959089000225504
+            "self": 0.05506386800061591
         },
         "TrainerController.start_learning": {
-            "total": 448.606838872,
+            "total": 1210.9176589979998,
             "count": 1,
-            "self": 0.5366459120032232,
+            "self": 1.4887348180291156,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.056270374000178,
+                    "total": 2.69649940599993,
                     "count": 1,
-                    "self": 2.056270374000178
+                    "self": 2.69649940599993
                 },
                 "TrainerController.advance": {
-                    "total": 445.92497908999667,
-                    "count": 18200,
-                    "self": 0.2633672639753968,
+                    "total": 1206.7314791489707,
+                    "count": 49947,
+                    "self": 0.6823276700042697,
                     "children": {
                         "env_step": {
-                            "total": 445.66161182602127,
-                            "count": 18200,
-                            "self": 271.6532638969966,
+                            "total": 1206.0491514789665,
+                            "count": 49947,
+                            "self": 737.1471806450636,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 173.7485385520472,
-                                    "count": 18200,
-                                    "self": 1.4044748550645636,
+                                    "total": 468.1690363379348,
+                                    "count": 49947,
+                                    "self": 3.8320324700207493,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 172.34406369698263,
-                                            "count": 18200,
-                                            "self": 172.34406369698263
+                                            "total": 464.33700386791406,
+                                            "count": 49947,
+                                            "self": 464.33700386791406
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.2598093769775005,
-                                    "count": 18200,
+                                    "total": 0.7329344959680384,
+                                    "count": 49946,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 447.5599846289806,
-                                            "count": 18200,
+                                            "total": 1208.074729278087,
+                                            "count": 49946,
                                             "is_parallel": true,
-                                            "self": 238.45577563399002,
+                                            "self": 640.0176559572346,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0022691120002491516,
+                                                            "total": 0.0031243229996107402,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007232300013129134,
+                                                            "self": 0.000868049997734488,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015458819989362382,
+                                                                    "total": 0.0022562730018762522,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015458819989362382
+                                                                    "self": 0.0022562730018762522
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0354464930001086,
+                                                            "total": 0.062033584999880986,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006147270000838034,
+                                                            "self": 0.0006183189998409944,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003884669999933976,
+                                                                    "total": 0.0003636130004451843,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003884669999933976
+                                                                    "self": 0.0003636130004451843
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.032559694000156014,
+                                                                    "total": 0.059257386999888695,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.032559694000156014
+                                                                    "self": 0.059257386999888695
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018836049998753879,
+                                                                    "total": 0.0017942659997061128,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003584909991332097,
+                                                                    "self": 0.000363535997166764,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015251140007421782,
+                                                                            "total": 0.0014307300025393488,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015251140007421782
+                                                                            "self": 0.0014307300025393488
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 209.10420899499059,
-                                                    "count": 18199,
+                                                    "total": 568.0570733208524,
+                                                    "count": 49945,
                                                     "is_parallel": true,
-                                                    "self": 9.693483582916997,
+                                                    "self": 26.529494731926206,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.035387233001529,
-                                                            "count": 18199,
+                                                            "total": 13.714483265988747,
+                                                            "count": 49945,
                                                             "is_parallel": true,
-                                                            "self": 5.035387233001529
+                                                            "self": 13.714483265988747
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 162.81739321303758,
-                                                            "count": 18199,
+                                                            "total": 442.40394648782694,
+                                                            "count": 49945,
                                                             "is_parallel": true,
-                                                            "self": 162.81739321303758
+                                                            "self": 442.40394648782694
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 31.557944966034484,
-                                                            "count": 18199,
+                                                            "total": 85.4091488351105,
+                                                            "count": 49945,
                                                             "is_parallel": true,
-                                                            "self": 5.869603582032141,
+                                                            "self": 15.943040161207136,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 25.688341384002342,
-                                                                    "count": 181990,
+                                                                    "total": 69.46610867390336,
+                                                                    "count": 499450,
                                                                     "is_parallel": true,
-                                                                    "self": 25.688341384002342
+                                                                    "self": 69.46610867390336
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 3.700799970829394e-05,
+                    "total": 4.186000023764791e-05,
                     "count": 1,
-                    "self": 3.700799970829394e-05,
+                    "self": 4.186000023764791e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 440.2358200241797,
-                                    "count": 693915,
+                                    "total": 1191.8636701597643,
+                                    "count": 1856394,
                                     "is_parallel": true,
-                                    "self": 14.564972983992902,
+                                    "self": 40.378412104681956,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 241.96448296518702,
-                                            "count": 693915,
+                                            "total": 650.2180409470811,
+                                            "count": 1856394,
                                             "is_parallel": true,
-                                            "self": 241.3043989621874,
+                                            "self": 648.546378143079,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.6600840029996107,
-                                                    "count": 4,
+                                                    "total": 1.6716628040021533,
+                                                    "count": 10,
                                                     "is_parallel": true,
-                                                    "self": 0.6600840029996107
+                                                    "self": 1.6716628040021533
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 183.70636407499978,
-                                            "count": 90,
+                                            "total": 501.2672171080012,
+                                            "count": 249,
                                             "is_parallel": true,
-                                            "self": 57.93966929200724,
+                                            "self": 154.72115953702723,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 125.76669478299254,
-                                                    "count": 4587,
+                                                    "total": 346.54605757097397,
+                                                    "count": 12696,
                                                     "is_parallel": true,
-                                                    "self": 125.76669478299254
+                                                    "self": 346.54605757097397
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08890648800024792,
+                    "total": 0.0009037649997480912,
                     "count": 1,
-                    "self": 0.0011352550000083284,
+                    "self": 2.32619995585992e-05,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08777123300023959,
+                            "total": 0.000880503000189492,
                             "count": 1,
-                            "self": 0.08777123300023959
+                            "self": 0.000880503000189492
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,59 +3,95 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.181818181818182,
-                "creation_time": 1731658843.591523,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 15.909090909090908,
+                "creation_time": 1731659940.6960835,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
                 "steps": 99960,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 21.636363636363637,
-                "creation_time": 1731658955.6826005,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 22.727272727272727,
+                "creation_time": 1731660050.0319004,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
                 "steps": 149984,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 25.09090909090909,
-                "creation_time": 1731659067.8287396,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1731660160.4481957,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
                 "steps": 199984,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.09090909090909,
-                "creation_time": 1731659178.1987424,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.727272727272727,
+                "creation_time": 1731660272.0411003,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.09090909090909,
-                "creation_time": 1731659178.326331,
+                "steps": 249944,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1731660383.4888308,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 26.727272727272727,
+                "creation_time": 1731660493.5284529,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1731660605.708579,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1731660714.2973912,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1731660824.1089575,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499976,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-499976.onnx",
+                "reward": 28.0,
+                "creation_time": 1731660932.8653169,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-499976.pt"
                 ]
             }
-        ],
-        "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
-            "reward": 25.09090909090909,
-            "creation_time": 1731659178.326331,
-            "auxillary_file_paths": [
-                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
-            ]
-        }
+        ]
     },
     "metadata": {
         "stats_format_version": "0.3.0",