Hugging Face's logo

Terps
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Terps commited on
Commit
b94b2bf
·
1 Parent(s): 1ace611

First Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +1 -1
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +1 -1
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +1 -1
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1694619472.84664ca06e8d.8721.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +2 -2
  16. run_logs/Player-0.log +7 -10
  17. run_logs/timers.json +141 -141
  18. run_logs/training_status.json +12 -12
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7d3546e32aeda62110d028a504229509b20202877174eecf9aff7da7a955c42
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76dd774faf42882541dc8350c37ce847692c609a81b78416794bdd0f03947d52
3
  size 646532
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d680e879c60c61e6540460163620dcd15aed10f9b2310878929d0db76a38bc05
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13bbc7d278f99c86c2183fd94d2b0e9fa453d1c01181999bb013f3b3fe82e752
3
  size 646532
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d477707aa339ce2107658d570f864a777cde263fa2f7989646b1f4c5206189f
3
  size 4648906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1187cdbc7212b505af4b386a8c30f635806b19d90e5894f2aca97291f669586
3
  size 4648906
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7d3546e32aeda62110d028a504229509b20202877174eecf9aff7da7a955c42
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76dd774faf42882541dc8350c37ce847692c609a81b78416794bdd0f03947d52
3
  size 646532
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d9968d6928d7938860a87b29ce0861f049d7802f6f30581ac594c23058aeea0
3
  size 4648906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71e2c39a7e96bab1ba1a956d9e427391c06f298f4b4d424094d91936dd399ce
3
  size 4648906
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7d3546e32aeda62110d028a504229509b20202877174eecf9aff7da7a955c42
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76dd774faf42882541dc8350c37ce847692c609a81b78416794bdd0f03947d52
3
  size 646532
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe48c12fcfece2b85eec40366c6c8c21e8dedff12f9193a16ad94e5e0855030f
3
  size 4648906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a81b457a8849a8a53fd446cfc539482a5a39fb9bb56ee13679f5808634d97af
3
  size 4648906
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46fea285be7aa473f9c4370c25af5e6a05fa6ae7885ee414eb32b6b27b41c7a0
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b02d0efa9c527262bdd2dbbf2b294fdac66e8c0f8a85c8aeae2ee78a37fc54
3
  size 646532
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7858edc42fa1026ff2b07ea34d1da94e2c6b05d1590396f469420f10153cd29d
3
  size 4648906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:006070d1b26d5ad7b61159cb7d3ac28e4a67822bdd8e571c7803aff16178253c
3
  size 4648906
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:881aebb1fb814e7765ea3d3518f3416b8bb96656ddc24e23e2cc503a76773149
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9de75d96d27c340e3fb6eddf78ac4493d7dd85221b5f33a2c0c50830151a29f8
3
  size 646532
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c82435a41b5f4b085339b269261bf85fa729e6bf74e9a42ef75be4c369f83cc3
3
  size 4648906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02143d42cbbbb81293fcbd8598c6cd54d7bcfea07ca4e2e5af2fc8bb5b64a658
3
  size 4648906
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe48c12fcfece2b85eec40366c6c8c21e8dedff12f9193a16ad94e5e0855030f
3
  size 4648906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a81b457a8849a8a53fd446cfc539482a5a39fb9bb56ee13679f5808634d97af
3
  size 4648906
SnowballTarget/events.out.tfevents.1694619472.84664ca06e8d.8721.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:137643d64ecb39fe91e649edf5592e28dd9aff6afa2fbf0ecceb4c9f10968524
3
+ size 29468
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 5e-05, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.05, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "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, "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": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
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}}, "curiosity": {"gamma": 0.99, "strength": 0.05, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "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, "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 CHANGED
@@ -5,7 +5,7 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
- learning_rate: 5.0e-05
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -81,7 +81,7 @@ checkpoint_settings:
81
  initialize_from: null
82
  load_model: false
83
  resume: false
84
- force: false
85
  train_model: false
86
  inference: false
87
  results_dir: results
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
81
  initialize_from: null
82
  load_model: false
83
  resume: false
84
+ force: true
85
  train_model: false
86
  inference: false
87
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.123 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.850551 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -169,7 +166,7 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 47
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -178,13 +175,13 @@ Memory Statistics:
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.7 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,10 +210,10 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 3687 frames, [64.0 KB-128.0 KB]: 1776 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.7 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.124 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.893295 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 36
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
 
175
  Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
  Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.8 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5121 frames, [64.0 KB-128.0 KB]: 342 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
  Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.7739371061325073,
6
- "min": 1.7739371061325073,
7
- "max": 2.8898189067840576,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 17054.630859375,
12
- "min": 17054.630859375,
13
- "max": 29785.59375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,27 +26,27 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 6.507968902587891,
30
- "min": 0.39943018555641174,
31
- "max": 6.567909240722656,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1269.053955078125,
36
- "min": 77.48945617675781,
37
- "max": 1339.853515625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Policy.CuriosityValueEstimate.mean": {
41
- "value": 0.2324235588312149,
42
- "min": 0.05569913238286972,
43
- "max": 0.272413045167923,
44
  "count": 20
45
  },
46
  "SnowballTarget.Policy.CuriosityValueEstimate.sum": {
47
- "value": 45.322593688964844,
48
- "min": 10.805631637573242,
49
- "max": 55.84467315673828,
50
  "count": 20
51
  },
52
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -62,39 +62,39 @@
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.PolicyLoss.mean": {
65
- "value": 0.06645068184297998,
66
- "min": 0.06293239985691745,
67
- "max": 0.07556281221075231,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.PolicyLoss.sum": {
71
- "value": 0.2658027273719199,
72
- "min": 0.2517295994276698,
73
- "max": 0.36155451173202463,
74
  "count": 20
75
  },
76
  "SnowballTarget.Losses.ValueLoss.mean": {
77
- "value": 0.14174404612504968,
78
- "min": 0.05566331118290477,
79
- "max": 0.15296241341560496,
80
  "count": 20
81
  },
82
  "SnowballTarget.Losses.ValueLoss.sum": {
83
- "value": 0.5669761845001987,
84
- "min": 0.22265324473161907,
85
- "max": 0.7007544597282129,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.LearningRate.mean": {
89
- "value": 1.347097306000001e-06,
90
- "min": 1.347097306000001e-06,
91
- "max": 4.8647002706e-05,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.LearningRate.sum": {
95
- "value": 5.388389224000004e-06,
96
- "min": 5.388389224000004e-06,
97
- "max": 0.00023086003828000004,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Epsilon.mean": {
@@ -122,63 +122,63 @@
122
  "count": 20
123
  },
124
  "SnowballTarget.Losses.CuriosityForwardLoss.mean": {
125
- "value": 0.0519607176675516,
126
- "min": 0.03753944684513936,
127
- "max": 0.12618426656962245,
128
  "count": 20
129
  },
130
  "SnowballTarget.Losses.CuriosityForwardLoss.sum": {
131
- "value": 0.2078428706702064,
132
- "min": 0.15015778738055743,
133
- "max": 0.5047370662784898,
134
  "count": 20
135
  },
136
  "SnowballTarget.Losses.CuriosityInverseLoss.mean": {
137
- "value": 1.3882069307215072,
138
- "min": 1.3882069307215072,
139
- "max": 2.7880861819813068,
140
  "count": 20
141
  },
142
  "SnowballTarget.Losses.CuriosityInverseLoss.sum": {
143
- "value": 5.552827722886029,
144
- "min": 5.552827722886029,
145
- "max": 13.346013092527205,
146
  "count": 20
147
  },
148
  "SnowballTarget.Environment.CumulativeReward.mean": {
149
- "value": 12.931818181818182,
150
- "min": 3.0454545454545454,
151
- "max": 13.113636363636363,
152
  "count": 20
153
  },
154
  "SnowballTarget.Environment.CumulativeReward.sum": {
155
- "value": 569.0,
156
- "min": 134.0,
157
- "max": 720.0,
158
  "count": 20
159
  },
160
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
161
- "value": 12.931818181818182,
162
- "min": 3.0454545454545454,
163
- "max": 13.113636363636363,
164
  "count": 20
165
  },
166
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
167
- "value": 569.0,
168
- "min": 134.0,
169
- "max": 720.0,
170
  "count": 20
171
  },
172
  "SnowballTarget.Policy.CuriosityReward.mean": {
173
- "value": 0.5269218775740062,
174
- "min": 0.3832893704581592,
175
- "max": 0.657959831031886,
176
  "count": 20
177
  },
178
  "SnowballTarget.Policy.CuriosityReward.sum": {
179
- "value": 23.184562613256276,
180
- "min": 17.248021670617163,
181
- "max": 36.18779070675373,
182
  "count": 20
183
  },
184
  "SnowballTarget.IsTraining.mean": {
@@ -196,67 +196,67 @@
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1694618216",
200
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
201
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
202
  "mlagents_version": "0.31.0.dev0",
203
  "mlagents_envs_version": "0.31.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
- "end_time_seconds": "1694618763"
208
  },
209
- "total": 546.4986369730001,
210
  "count": 1,
211
- "self": 0.4405676350000931,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.0675821500000211,
215
  "count": 1,
216
- "self": 0.0675821500000211
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 545.990487188,
220
  "count": 1,
221
- "self": 0.6146442020152563,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 4.925381731000016,
225
  "count": 1,
226
- "self": 4.925381731000016
227
  },
228
  "TrainerController.advance": {
229
- "total": 540.3025855939845,
230
- "count": 18209,
231
- "self": 0.2996432489791232,
232
  "children": {
233
  "env_step": {
234
- "total": 540.0029423450054,
235
- "count": 18209,
236
- "self": 417.8532004489799,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 121.84720654902344,
240
- "count": 18209,
241
- "self": 1.812279768020744,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 120.0349267810027,
245
- "count": 18209,
246
- "self": 120.0349267810027
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 0.3025353470020491,
252
- "count": 18209,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 544.3407843360197,
257
- "count": 18209,
258
  "is_parallel": true,
259
- "self": 288.2979362780077,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
@@ -265,48 +265,48 @@
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
- "total": 0.007067042000016954,
269
  "count": 1,
270
  "is_parallel": true,
271
- "self": 0.0047269639998148705,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
- "total": 0.002340078000202084,
275
  "count": 10,
276
  "is_parallel": true,
277
- "self": 0.002340078000202084
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
- "total": 0.048748401000011654,
283
  "count": 1,
284
  "is_parallel": true,
285
- "self": 0.00047814000015478086,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
- "total": 0.00033038599997325946,
289
  "count": 1,
290
  "is_parallel": true,
291
- "self": 0.00033038599997325946
292
  },
293
  "communicator.exchange": {
294
- "total": 0.04524965899997824,
295
  "count": 1,
296
  "is_parallel": true,
297
- "self": 0.04524965899997824
298
  },
299
  "steps_from_proto": {
300
- "total": 0.0026902159999053765,
301
  "count": 1,
302
  "is_parallel": true,
303
- "self": 0.0013067759999785267,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
- "total": 0.0013834399999268499,
307
  "count": 10,
308
  "is_parallel": true,
309
- "self": 0.0013834399999268499
310
  }
311
  }
312
  }
@@ -315,34 +315,34 @@
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
- "total": 256.04284805801205,
319
- "count": 18208,
320
  "is_parallel": true,
321
- "self": 10.82011929900716,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
- "total": 5.415828948010358,
325
- "count": 18208,
326
  "is_parallel": true,
327
- "self": 5.415828948010358
328
  },
329
  "communicator.exchange": {
330
- "total": 202.2562164839893,
331
- "count": 18208,
332
  "is_parallel": true,
333
- "self": 202.2562164839893
334
  },
335
  "steps_from_proto": {
336
- "total": 37.55068332700523,
337
- "count": 18208,
338
  "is_parallel": true,
339
- "self": 7.081580279027548,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
- "total": 30.469103047977683,
343
- "count": 182080,
344
  "is_parallel": true,
345
- "self": 30.469103047977683
346
  }
347
  }
348
  }
@@ -357,9 +357,9 @@
357
  }
358
  },
359
  "trainer_threads": {
360
- "total": 0.00012079400016773434,
361
  "count": 1,
362
- "self": 0.00012079400016773434,
363
  "children": {
364
  "thread_root": {
365
  "total": 0.0,
@@ -368,36 +368,36 @@
368
  "self": 0.0,
369
  "children": {
370
  "trainer_advance": {
371
- "total": 537.2016064389948,
372
- "count": 384349,
373
  "is_parallel": true,
374
- "self": 8.750835011033132,
375
  "children": {
376
  "process_trajectory": {
377
- "total": 275.66332465996163,
378
- "count": 384349,
379
  "is_parallel": true,
380
- "self": 273.6291796439617,
381
  "children": {
382
  "RLTrainer._checkpoint": {
383
- "total": 2.0341450159999113,
384
  "count": 4,
385
  "is_parallel": true,
386
- "self": 2.0341450159999113
387
  }
388
  }
389
  },
390
  "_update_policy": {
391
- "total": 252.787446768,
392
  "count": 90,
393
  "is_parallel": true,
394
- "self": 159.73786780600722,
395
  "children": {
396
  "TorchPPOOptimizer.update": {
397
- "total": 93.04957896199278,
398
  "count": 4584,
399
  "is_parallel": true,
400
- "self": 93.04957896199278
401
  }
402
  }
403
  }
@@ -408,14 +408,14 @@
408
  }
409
  },
410
  "TrainerController._save_models": {
411
- "total": 0.1477548670000033,
412
  "count": 1,
413
- "self": 0.0008560940000279516,
414
  "children": {
415
  "RLTrainer._checkpoint": {
416
- "total": 0.14689877299997534,
417
  "count": 1,
418
- "self": 0.14689877299997534
419
  }
420
  }
421
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9894982576370239,
6
+ "min": 0.9754210710525513,
7
+ "max": 2.8669533729553223,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9480.3828125,
12
+ "min": 9480.3828125,
13
+ "max": 29549.6875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.786215782165527,
30
+ "min": 0.4517129361629486,
31
+ "max": 12.806447982788086,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2493.31201171875,
36
+ "min": 87.63230895996094,
37
+ "max": 2617.53857421875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Policy.CuriosityValueEstimate.mean": {
41
+ "value": 0.17987486720085144,
42
+ "min": 0.10761666297912598,
43
+ "max": 0.26051655411720276,
44
  "count": 20
45
  },
46
  "SnowballTarget.Policy.CuriosityValueEstimate.sum": {
47
+ "value": 35.075599670410156,
48
+ "min": 20.87763214111328,
49
+ "max": 53.40589141845703,
50
  "count": 20
51
  },
52
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.PolicyLoss.mean": {
65
+ "value": 0.06864661709208604,
66
+ "min": 0.06325657534191623,
67
+ "max": 0.07433176024967586,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.PolicyLoss.sum": {
71
+ "value": 0.27458646836834416,
72
+ "min": 0.2530263013676649,
73
+ "max": 0.3716588012483793,
74
  "count": 20
75
  },
76
  "SnowballTarget.Losses.ValueLoss.mean": {
77
+ "value": 0.10565935024151614,
78
+ "min": 0.05770217951537822,
79
+ "max": 0.16127740534972038,
80
  "count": 20
81
  },
82
  "SnowballTarget.Losses.ValueLoss.sum": {
83
+ "value": 0.42263740096606456,
84
+ "min": 0.23080871806151287,
85
+ "max": 0.8063870267486019,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.LearningRate.mean": {
89
+ "value": 8.082097306000005e-06,
90
+ "min": 8.082097306000005e-06,
91
+ "max": 0.000291882002706,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.LearningRate.sum": {
95
+ "value": 3.232838922400002e-05,
96
+ "min": 3.232838922400002e-05,
97
+ "max": 0.00138516003828,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Epsilon.mean": {
 
122
  "count": 20
123
  },
124
  "SnowballTarget.Losses.CuriosityForwardLoss.mean": {
125
+ "value": 0.03605778130027009,
126
+ "min": 0.035578419041692046,
127
+ "max": 0.1175546848680824,
128
  "count": 20
129
  },
130
  "SnowballTarget.Losses.CuriosityForwardLoss.sum": {
131
+ "value": 0.14423112520108036,
132
+ "min": 0.14423112520108036,
133
+ "max": 0.4702187394723296,
134
  "count": 20
135
  },
136
  "SnowballTarget.Losses.CuriosityInverseLoss.mean": {
137
+ "value": 0.8827689254985136,
138
+ "min": 0.8652849678899728,
139
+ "max": 2.7858384264012175,
140
  "count": 20
141
  },
142
  "SnowballTarget.Losses.CuriosityInverseLoss.sum": {
143
+ "value": 3.5310757019940544,
144
+ "min": 3.4890115354575366,
145
+ "max": 13.03318906765358,
146
  "count": 20
147
  },
148
  "SnowballTarget.Environment.CumulativeReward.mean": {
149
+ "value": 25.022727272727273,
150
+ "min": 3.2954545454545454,
151
+ "max": 25.022727272727273,
152
  "count": 20
153
  },
154
  "SnowballTarget.Environment.CumulativeReward.sum": {
155
+ "value": 1101.0,
156
+ "min": 145.0,
157
+ "max": 1375.0,
158
  "count": 20
159
  },
160
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
161
+ "value": 25.022727272727273,
162
+ "min": 3.2954545454545454,
163
+ "max": 25.022727272727273,
164
  "count": 20
165
  },
166
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
167
+ "value": 1101.0,
168
+ "min": 145.0,
169
+ "max": 1375.0,
170
  "count": 20
171
  },
172
  "SnowballTarget.Policy.CuriosityReward.mean": {
173
+ "value": 0.37121628858784045,
174
+ "min": 0.36311526602049443,
175
+ "max": 0.6572515787048774,
176
  "count": 20
177
  },
178
  "SnowballTarget.Policy.CuriosityReward.sum": {
179
+ "value": 16.33351669786498,
180
+ "min": 16.193131546955556,
181
+ "max": 36.14883682876825,
182
  "count": 20
183
  },
184
  "SnowballTarget.IsTraining.mean": {
 
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1694619470",
200
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
201
+ "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",
202
  "mlagents_version": "0.31.0.dev0",
203
  "mlagents_envs_version": "0.31.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1694620008"
208
  },
209
+ "total": 537.871770708,
210
  "count": 1,
211
+ "self": 0.42486783499998637,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.07099536200007606,
215
  "count": 1,
216
+ "self": 0.07099536200007606
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 537.3759075109999,
220
  "count": 1,
221
+ "self": 0.5942737139978362,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 4.729345418999856,
225
  "count": 1,
226
+ "self": 4.729345418999856
227
  },
228
  "TrainerController.advance": {
229
+ "total": 531.9056004700019,
230
+ "count": 18207,
231
+ "self": 0.28875258900757217,
232
  "children": {
233
  "env_step": {
234
+ "total": 531.6168478809943,
235
+ "count": 18207,
236
+ "self": 410.4874470380071,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 120.82789380598388,
240
+ "count": 18207,
241
+ "self": 1.8920219630301744,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 118.9358718429537,
245
+ "count": 18207,
246
+ "self": 118.9358718429537
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 0.30150703700337544,
252
+ "count": 18207,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 535.6665731939938,
257
+ "count": 18207,
258
  "is_parallel": true,
259
+ "self": 284.15536370497443,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.003331277999905069,
269
  "count": 1,
270
  "is_parallel": true,
271
+ "self": 0.0008317099998293997,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.0024995680000756693,
275
  "count": 10,
276
  "is_parallel": true,
277
+ "self": 0.0024995680000756693
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.04511771600004977,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.0007030890001260559,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.00042302299993934867,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.00042302299993934867
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.04046062499992331,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.04046062499992331
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.003530979000061052,
301
  "count": 1,
302
  "is_parallel": true,
303
+ "self": 0.0015479049998248229,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.001983074000236229,
307
  "count": 10,
308
  "is_parallel": true,
309
+ "self": 0.001983074000236229
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
+ "total": 251.5112094890194,
319
+ "count": 18206,
320
  "is_parallel": true,
321
+ "self": 10.637280265021445,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
+ "total": 5.376301449994344,
325
+ "count": 18206,
326
  "is_parallel": true,
327
+ "self": 5.376301449994344
328
  },
329
  "communicator.exchange": {
330
+ "total": 198.88422318497965,
331
+ "count": 18206,
332
  "is_parallel": true,
333
+ "self": 198.88422318497965
334
  },
335
  "steps_from_proto": {
336
+ "total": 36.61340458902396,
337
+ "count": 18206,
338
  "is_parallel": true,
339
+ "self": 6.762891233860273,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
+ "total": 29.850513355163685,
343
+ "count": 182060,
344
  "is_parallel": true,
345
+ "self": 29.850513355163685
346
  }
347
  }
348
  }
 
357
  }
358
  },
359
  "trainer_threads": {
360
+ "total": 0.00011929000038435333,
361
  "count": 1,
362
+ "self": 0.00011929000038435333,
363
  "children": {
364
  "thread_root": {
365
  "total": 0.0,
 
368
  "self": 0.0,
369
  "children": {
370
  "trainer_advance": {
371
+ "total": 528.7277012818795,
372
+ "count": 395869,
373
  "is_parallel": true,
374
+ "self": 8.865601085034768,
375
  "children": {
376
  "process_trajectory": {
377
+ "total": 270.5945444238446,
378
+ "count": 395869,
379
  "is_parallel": true,
380
+ "self": 269.1041468868448,
381
  "children": {
382
  "RLTrainer._checkpoint": {
383
+ "total": 1.490397536999808,
384
  "count": 4,
385
  "is_parallel": true,
386
+ "self": 1.490397536999808
387
  }
388
  }
389
  },
390
  "_update_policy": {
391
+ "total": 249.26755577300014,
392
  "count": 90,
393
  "is_parallel": true,
394
+ "self": 155.99453570301625,
395
  "children": {
396
  "TorchPPOOptimizer.update": {
397
+ "total": 93.27302006998389,
398
  "count": 4584,
399
  "is_parallel": true,
400
+ "self": 93.27302006998389
401
  }
402
  }
403
  }
 
408
  }
409
  },
410
  "TrainerController._save_models": {
411
+ "total": 0.14656861799994658,
412
  "count": 1,
413
+ "self": 0.0010552509997978632,
414
  "children": {
415
  "RLTrainer._checkpoint": {
416
+ "total": 0.14551336700014872,
417
  "count": 1,
418
+ "self": 0.14551336700014872
419
  }
420
  }
421
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 6.909090909090909,
8
- "creation_time": 1694618357.7133837,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 11.363636363636363,
17
- "creation_time": 1694618490.2798183,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 12.454545454545455,
26
- "creation_time": 1694618628.515462,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 15.0,
35
- "creation_time": 1694618762.8146782,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 15.0,
44
- "creation_time": 1694618762.9890928,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 15.0,
54
- "creation_time": 1694618762.9890928,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 13.545454545454545,
8
+ "creation_time": 1694619608.0852468,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 24.0,
17
+ "creation_time": 1694619738.5600145,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.272727272727273,
26
+ "creation_time": 1694619876.8527107,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 24.09090909090909,
35
+ "creation_time": 1694620008.1859448,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
 
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 24.09090909090909,
44
+ "creation_time": 1694620008.3675275,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 24.09090909090909,
54
+ "creation_time": 1694620008.3675275,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]