step 200000
Browse files- SnowballTarget.onnx +1 -1
- SnowballTarget/SnowballTarget-149984.onnx +3 -0
- SnowballTarget/SnowballTarget-149984.pt +3 -0
- SnowballTarget/SnowballTarget-199984.onnx +3 -0
- SnowballTarget/SnowballTarget-199984.pt +3 -0
- SnowballTarget/SnowballTarget-200112.onnx +3 -0
- SnowballTarget/SnowballTarget-200112.pt +3 -0
- SnowballTarget/SnowballTarget-49936.onnx +1 -1
- SnowballTarget/SnowballTarget-49936.pt +1 -1
- SnowballTarget/SnowballTarget-99960.onnx +1 -1
- SnowballTarget/SnowballTarget-99960.pt +1 -1
- SnowballTarget/checkpoint.pt +1 -1
- SnowballTarget/events.out.tfevents.1711017539.35054b78594f.7520.0 +3 -0
- config.json +1 -1
- configuration.yaml +2 -2
- run_logs/Player-0.log +14 -14
- run_logs/timers.json +161 -161
- run_logs/training_status.json +36 -18
SnowballTarget.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 650646
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a5bf727a71a172e02098feb4dceacdf645c89f35582015aee09f11d32d8149
|
3 |
size 650646
|
SnowballTarget/SnowballTarget-149984.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8134542fb004d9126317924508485c6486cde2f64a327e302169f1a7ca81de66
|
3 |
+
size 650646
|
SnowballTarget/SnowballTarget-149984.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e86d9a1fd5113d57f8d533c92b65723ac6724e459c0acbfd08e60c1fc6767bab
|
3 |
+
size 3850075
|
SnowballTarget/SnowballTarget-199984.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a5bf727a71a172e02098feb4dceacdf645c89f35582015aee09f11d32d8149
|
3 |
+
size 650646
|
SnowballTarget/SnowballTarget-199984.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bbd8cbfc29d4cd62c388f0f2cc5d817eca4322bd132bd31df505bafd94f4f3b
|
3 |
+
size 3850075
|
SnowballTarget/SnowballTarget-200112.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a5bf727a71a172e02098feb4dceacdf645c89f35582015aee09f11d32d8149
|
3 |
+
size 650646
|
SnowballTarget/SnowballTarget-200112.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b41ff5bedffafcb681dbb106788b4d2acbe798162ccadd7c7c779a006142bd98
|
3 |
+
size 3850075
|
SnowballTarget/SnowballTarget-49936.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 650646
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8df1b2fce5df7c556f63147dcc3e5d4aa001a88d83f6f7d4db908e08217a6ba2
|
3 |
size 650646
|
SnowballTarget/SnowballTarget-49936.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3850000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76c1bbb9366fcb32af1a5fee63e41fb443d74c48512ab34ecbb8d8a64e606677
|
3 |
size 3850000
|
SnowballTarget/SnowballTarget-99960.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 650646
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aa000145ef8d5883584d3fbe6277f7799312b14fa2ae5b24b4a8f68119e89b8
|
3 |
size 650646
|
SnowballTarget/SnowballTarget-99960.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3850000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9eab55e7e34f6ae38c211e653390c1654103a61e4ee10409546e853a4a0d46e
|
3 |
size 3850000
|
SnowballTarget/checkpoint.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3849250
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38b0bf2ec7ebc6624abb87fc719ee75caa4bb189dfb172b7094adee87bd43826
|
3 |
size 3849250
|
SnowballTarget/events.out.tfevents.1711017539.35054b78594f.7520.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:196eea9b50cf3d48bde3a7c80820a73e4624acde6ed2db12a726e1bde82d08da
|
3 |
+
size 19471
|
config.json
CHANGED
@@ -1 +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":
|
|
|
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": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
|
configuration.yaml
CHANGED
@@ -38,7 +38,7 @@ behaviors:
|
|
38 |
init_path: null
|
39 |
keep_checkpoints: 10
|
40 |
even_checkpoints: false
|
41 |
-
max_steps:
|
42 |
time_horizon: 64
|
43 |
summary_freq: 10000
|
44 |
threaded: true
|
@@ -66,7 +66,7 @@ engine_settings:
|
|
66 |
no_graphics_monitor: false
|
67 |
environment_parameters: null
|
68 |
checkpoint_settings:
|
69 |
-
run_id:
|
70 |
initialize_from: null
|
71 |
load_model: false
|
72 |
resume: false
|
|
|
38 |
init_path: null
|
39 |
keep_checkpoints: 10
|
40 |
even_checkpoints: false
|
41 |
+
max_steps: 200000
|
42 |
time_horizon: 64
|
43 |
summary_freq: 10000
|
44 |
threaded: true
|
|
|
66 |
no_graphics_monitor: false
|
67 |
environment_parameters: null
|
68 |
checkpoint_settings:
|
69 |
+
run_id: SnowballTarget2
|
70 |
initialize_from: null
|
71 |
load_model: false
|
72 |
resume: false
|
run_logs/Player-0.log
CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
|
|
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.
|
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)
|
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
|
|
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.
|
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.
|
@@ -50,7 +50,7 @@ Memory Statistics:
|
|
50 |
[ALLOC_TEMP_TLS] TLS Allocator
|
51 |
StackAllocators :
|
52 |
[ALLOC_TEMP_MAIN]
|
53 |
-
Peak usage frame count: [8.0 KB-16.0 KB]:
|
54 |
Initial Block Size 4.0 MB
|
55 |
Current Block Size 4.0 MB
|
56 |
Peak Allocated Bytes 2.0 MB
|
@@ -166,22 +166,22 @@ Memory Statistics:
|
|
166 |
Peak Allocated Bytes 0 B
|
167 |
Overflow Count 0
|
168 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
169 |
-
Peak main deferred allocation count
|
170 |
[ALLOC_BUCKET]
|
171 |
Large Block size 4.0 MB
|
172 |
Used Block count 1
|
173 |
Peak Allocated bytes 1.0 MB
|
174 |
[ALLOC_DEFAULT_MAIN]
|
175 |
-
Peak usage frame count: [4.0 MB-8.0 MB]:
|
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]:
|
182 |
Requested Block Size 16.0 MB
|
183 |
Peak Block count 1
|
184 |
-
Peak Allocated memory 17.
|
185 |
Peak Large allocation bytes 16.0 MB
|
186 |
[ALLOC_TEMP_JOB_1_FRAME]
|
187 |
Initial Block Size 2.0 MB
|
@@ -210,13 +210,13 @@ Memory Statistics:
|
|
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]:
|
214 |
Requested Block Size 16.0 MB
|
215 |
Peak Block count 1
|
216 |
-
Peak Allocated memory 67.
|
217 |
Peak Large allocation bytes 0 B
|
218 |
[ALLOC_GFX_THREAD]
|
219 |
-
Peak usage frame count: [32.0 KB-64.0 KB]:
|
220 |
Requested Block Size 16.0 MB
|
221 |
Peak Block count 1
|
222 |
Peak Allocated memory 39.6 KB
|
@@ -228,13 +228,13 @@ Memory Statistics:
|
|
228 |
Used Block count 1
|
229 |
Peak Allocated bytes 1.0 MB
|
230 |
[ALLOC_CACHEOBJECTS_MAIN]
|
231 |
-
Peak usage frame count: [0.5 MB-1.0 MB]:
|
232 |
Requested Block Size 4.0 MB
|
233 |
Peak Block count 1
|
234 |
Peak Allocated memory 0.6 MB
|
235 |
Peak Large allocation bytes 0 B
|
236 |
[ALLOC_CACHEOBJECTS_THREAD]
|
237 |
-
Peak usage frame count: [0.5 MB-1.0 MB]:
|
238 |
Requested Block Size 4.0 MB
|
239 |
Peak Block count 1
|
240 |
Peak Allocated memory 2.2 MB
|
@@ -246,13 +246,13 @@ Memory Statistics:
|
|
246 |
Used Block count 1
|
247 |
Peak Allocated bytes 1.0 MB
|
248 |
[ALLOC_TYPETREE_MAIN]
|
249 |
-
Peak usage frame count: [0-1.0 KB]:
|
250 |
Requested Block Size 2.0 MB
|
251 |
Peak Block count 1
|
252 |
Peak Allocated memory 1.0 KB
|
253 |
Peak Large allocation bytes 0 B
|
254 |
[ALLOC_TYPETREE_THREAD]
|
255 |
-
Peak usage frame count: [1.0 KB-2.0 KB]:
|
256 |
Requested Block Size 2.0 MB
|
257 |
Peak Block count 1
|
258 |
Peak Allocated memory 1.7 KB
|
|
|
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 0.091 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: 0.696377 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.
|
|
|
50 |
[ALLOC_TEMP_TLS] TLS Allocator
|
51 |
StackAllocators :
|
52 |
[ALLOC_TEMP_MAIN]
|
53 |
+
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
|
54 |
Initial Block Size 4.0 MB
|
55 |
Current Block Size 4.0 MB
|
56 |
Peak Allocated Bytes 2.0 MB
|
|
|
166 |
Peak Allocated Bytes 0 B
|
167 |
Overflow Count 0
|
168 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
169 |
+
Peak main deferred allocation count 41
|
170 |
[ALLOC_BUCKET]
|
171 |
Large Block size 4.0 MB
|
172 |
Used Block count 1
|
173 |
Peak Allocated bytes 1.0 MB
|
174 |
[ALLOC_DEFAULT_MAIN]
|
175 |
+
Peak usage frame count: [4.0 MB-8.0 MB]: 5460 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]: 5460 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]: 4575 frames, [64.0 KB-128.0 KB]: 885 frames
|
214 |
Requested Block Size 16.0 MB
|
215 |
Peak Block count 1
|
216 |
+
Peak Allocated memory 67.3 KB
|
217 |
Peak Large allocation bytes 0 B
|
218 |
[ALLOC_GFX_THREAD]
|
219 |
+
Peak usage frame count: [32.0 KB-64.0 KB]: 5460 frames
|
220 |
Requested Block Size 16.0 MB
|
221 |
Peak Block count 1
|
222 |
Peak Allocated memory 39.6 KB
|
|
|
228 |
Used Block count 1
|
229 |
Peak Allocated bytes 1.0 MB
|
230 |
[ALLOC_CACHEOBJECTS_MAIN]
|
231 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames
|
232 |
Requested Block Size 4.0 MB
|
233 |
Peak Block count 1
|
234 |
Peak Allocated memory 0.6 MB
|
235 |
Peak Large allocation bytes 0 B
|
236 |
[ALLOC_CACHEOBJECTS_THREAD]
|
237 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
|
238 |
Requested Block Size 4.0 MB
|
239 |
Peak Block count 1
|
240 |
Peak Allocated memory 2.2 MB
|
|
|
246 |
Used Block count 1
|
247 |
Peak Allocated bytes 1.0 MB
|
248 |
[ALLOC_TYPETREE_MAIN]
|
249 |
+
Peak usage frame count: [0-1.0 KB]: 5460 frames
|
250 |
Requested Block Size 2.0 MB
|
251 |
Peak Block count 1
|
252 |
Peak Allocated memory 1.0 KB
|
253 |
Peak Large allocation bytes 0 B
|
254 |
[ALLOC_TYPETREE_THREAD]
|
255 |
+
Peak usage frame count: [1.0 KB-2.0 KB]: 5460 frames
|
256 |
Requested Block Size 2.0 MB
|
257 |
Peak Block count 1
|
258 |
Peak Allocated memory 1.7 KB
|
run_logs/timers.json
CHANGED
@@ -2,213 +2,213 @@
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"SnowballTarget.Policy.Entropy.mean": {
|
5 |
-
"value":
|
6 |
-
"min":
|
7 |
-
"max": 2.
|
8 |
-
"count":
|
9 |
},
|
10 |
"SnowballTarget.Policy.Entropy.sum": {
|
11 |
-
"value":
|
12 |
-
"min":
|
13 |
-
"max":
|
14 |
-
"count":
|
15 |
},
|
16 |
"SnowballTarget.Step.mean": {
|
17 |
-
"value":
|
18 |
"min": 9952.0,
|
19 |
-
"max":
|
20 |
-
"count":
|
21 |
},
|
22 |
"SnowballTarget.Step.sum": {
|
23 |
-
"value":
|
24 |
"min": 9952.0,
|
25 |
-
"max":
|
26 |
-
"count":
|
27 |
},
|
28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
-
"value":
|
30 |
-
"min": 0.
|
31 |
-
"max":
|
32 |
-
"count":
|
33 |
},
|
34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
-
"value":
|
36 |
-
"min":
|
37 |
-
"max":
|
38 |
-
"count":
|
39 |
},
|
40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
41 |
"value": 199.0,
|
42 |
"min": 199.0,
|
43 |
"max": 199.0,
|
44 |
-
"count":
|
45 |
},
|
46 |
"SnowballTarget.Environment.EpisodeLength.sum": {
|
47 |
-
"value":
|
48 |
"min": 8756.0,
|
49 |
"max": 10945.0,
|
50 |
-
"count":
|
51 |
},
|
52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
53 |
-
"value": 0.
|
54 |
-
"min": 0.
|
55 |
-
"max": 0.
|
56 |
-
"count":
|
57 |
},
|
58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
59 |
-
"value": 0.
|
60 |
-
"min": 0.
|
61 |
-
"max": 0.
|
62 |
-
"count":
|
63 |
},
|
64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
65 |
-
"value": 0.
|
66 |
-
"min": 0.
|
67 |
-
"max": 0.
|
68 |
-
"count":
|
69 |
},
|
70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
71 |
-
"value":
|
72 |
-
"min": 0.
|
73 |
-
"max": 1.
|
74 |
-
"count":
|
75 |
},
|
76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
77 |
-
"value":
|
78 |
-
"min":
|
79 |
-
"max": 0.
|
80 |
-
"count":
|
81 |
},
|
82 |
"SnowballTarget.Policy.LearningRate.sum": {
|
83 |
-
"value":
|
84 |
-
"min":
|
85 |
-
"max": 0.
|
86 |
-
"count":
|
87 |
},
|
88 |
"SnowballTarget.Policy.Epsilon.mean": {
|
89 |
-
"value": 0.
|
90 |
-
"min": 0.
|
91 |
-
"max": 0.
|
92 |
-
"count":
|
93 |
},
|
94 |
"SnowballTarget.Policy.Epsilon.sum": {
|
95 |
-
"value": 0.
|
96 |
-
"min": 0.
|
97 |
-
"max": 0.
|
98 |
-
"count":
|
99 |
},
|
100 |
"SnowballTarget.Policy.Beta.mean": {
|
101 |
-
"value": 0.
|
102 |
-
"min": 0.
|
103 |
-
"max": 0.
|
104 |
-
"count":
|
105 |
},
|
106 |
"SnowballTarget.Policy.Beta.sum": {
|
107 |
-
"value": 0.
|
108 |
-
"min": 0.
|
109 |
-
"max": 0.
|
110 |
-
"count":
|
111 |
},
|
112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
113 |
-
"value":
|
114 |
-
"min": 3.
|
115 |
-
"max":
|
116 |
-
"count":
|
117 |
},
|
118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
119 |
-
"value":
|
120 |
-
"min":
|
121 |
-
"max":
|
122 |
-
"count":
|
123 |
},
|
124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
125 |
-
"value":
|
126 |
-
"min": 3.
|
127 |
-
"max":
|
128 |
-
"count":
|
129 |
},
|
130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
131 |
-
"value":
|
132 |
-
"min":
|
133 |
-
"max":
|
134 |
-
"count":
|
135 |
},
|
136 |
"SnowballTarget.IsTraining.mean": {
|
137 |
"value": 1.0,
|
138 |
"min": 1.0,
|
139 |
"max": 1.0,
|
140 |
-
"count":
|
141 |
},
|
142 |
"SnowballTarget.IsTraining.sum": {
|
143 |
"value": 1.0,
|
144 |
"min": 1.0,
|
145 |
"max": 1.0,
|
146 |
-
"count":
|
147 |
}
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
-
"start_time_seconds": "
|
152 |
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
|
153 |
-
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=
|
154 |
"mlagents_version": "1.1.0.dev0",
|
155 |
"mlagents_envs_version": "1.1.0.dev0",
|
156 |
"communication_protocol_version": "1.5.0",
|
157 |
"pytorch_version": "2.2.1+cu121",
|
158 |
"numpy_version": "1.23.5",
|
159 |
-
"end_time_seconds": "
|
160 |
},
|
161 |
-
"total":
|
162 |
"count": 1,
|
163 |
-
"self": 0.
|
164 |
"children": {
|
165 |
"run_training.setup": {
|
166 |
-
"total": 0.
|
167 |
"count": 1,
|
168 |
-
"self": 0.
|
169 |
},
|
170 |
"TrainerController.start_learning": {
|
171 |
-
"total":
|
172 |
"count": 1,
|
173 |
-
"self": 0.
|
174 |
"children": {
|
175 |
"TrainerController._reset_env": {
|
176 |
-
"total":
|
177 |
"count": 1,
|
178 |
-
"self":
|
179 |
},
|
180 |
"TrainerController.advance": {
|
181 |
-
"total":
|
182 |
-
"count":
|
183 |
-
"self": 0.
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
-
"total":
|
187 |
-
"count":
|
188 |
-
"self":
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
-
"total":
|
192 |
-
"count":
|
193 |
-
"self":
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
-
"total":
|
197 |
-
"count":
|
198 |
-
"self":
|
199 |
}
|
200 |
}
|
201 |
},
|
202 |
"workers": {
|
203 |
-
"total": 0.
|
204 |
-
"count":
|
205 |
"self": 0.0,
|
206 |
"children": {
|
207 |
"worker_root": {
|
208 |
-
"total":
|
209 |
-
"count":
|
210 |
"is_parallel": true,
|
211 |
-
"self":
|
212 |
"children": {
|
213 |
"run_training.setup": {
|
214 |
"total": 0.0,
|
@@ -217,48 +217,48 @@
|
|
217 |
"self": 0.0,
|
218 |
"children": {
|
219 |
"steps_from_proto": {
|
220 |
-
"total": 0.
|
221 |
"count": 1,
|
222 |
"is_parallel": true,
|
223 |
-
"self": 0.
|
224 |
"children": {
|
225 |
"_process_rank_one_or_two_observation": {
|
226 |
-
"total": 0.
|
227 |
"count": 10,
|
228 |
"is_parallel": true,
|
229 |
-
"self": 0.
|
230 |
}
|
231 |
}
|
232 |
},
|
233 |
"UnityEnvironment.step": {
|
234 |
-
"total": 0.
|
235 |
"count": 1,
|
236 |
"is_parallel": true,
|
237 |
-
"self": 0.
|
238 |
"children": {
|
239 |
"UnityEnvironment._generate_step_input": {
|
240 |
-
"total": 0.
|
241 |
"count": 1,
|
242 |
"is_parallel": true,
|
243 |
-
"self": 0.
|
244 |
},
|
245 |
"communicator.exchange": {
|
246 |
-
"total": 0.
|
247 |
"count": 1,
|
248 |
"is_parallel": true,
|
249 |
-
"self": 0.
|
250 |
},
|
251 |
"steps_from_proto": {
|
252 |
-
"total": 0.
|
253 |
"count": 1,
|
254 |
"is_parallel": true,
|
255 |
-
"self": 0.
|
256 |
"children": {
|
257 |
"_process_rank_one_or_two_observation": {
|
258 |
-
"total": 0.
|
259 |
"count": 10,
|
260 |
"is_parallel": true,
|
261 |
-
"self": 0.
|
262 |
}
|
263 |
}
|
264 |
}
|
@@ -267,34 +267,34 @@
|
|
267 |
}
|
268 |
},
|
269 |
"UnityEnvironment.step": {
|
270 |
-
"total":
|
271 |
-
"count":
|
272 |
"is_parallel": true,
|
273 |
-
"self":
|
274 |
"children": {
|
275 |
"UnityEnvironment._generate_step_input": {
|
276 |
-
"total":
|
277 |
-
"count":
|
278 |
"is_parallel": true,
|
279 |
-
"self":
|
280 |
},
|
281 |
"communicator.exchange": {
|
282 |
-
"total":
|
283 |
-
"count":
|
284 |
"is_parallel": true,
|
285 |
-
"self":
|
286 |
},
|
287 |
"steps_from_proto": {
|
288 |
-
"total":
|
289 |
-
"count":
|
290 |
"is_parallel": true,
|
291 |
-
"self":
|
292 |
"children": {
|
293 |
"_process_rank_one_or_two_observation": {
|
294 |
-
"total":
|
295 |
-
"count":
|
296 |
"is_parallel": true,
|
297 |
-
"self":
|
298 |
}
|
299 |
}
|
300 |
}
|
@@ -309,9 +309,9 @@
|
|
309 |
}
|
310 |
},
|
311 |
"trainer_threads": {
|
312 |
-
"total": 0.
|
313 |
"count": 1,
|
314 |
-
"self": 0.
|
315 |
"children": {
|
316 |
"thread_root": {
|
317 |
"total": 0.0,
|
@@ -320,36 +320,36 @@
|
|
320 |
"self": 0.0,
|
321 |
"children": {
|
322 |
"trainer_advance": {
|
323 |
-
"total":
|
324 |
-
"count":
|
325 |
"is_parallel": true,
|
326 |
-
"self":
|
327 |
"children": {
|
328 |
"process_trajectory": {
|
329 |
-
"total":
|
330 |
-
"count":
|
331 |
"is_parallel": true,
|
332 |
-
"self":
|
333 |
"children": {
|
334 |
"RLTrainer._checkpoint": {
|
335 |
-
"total": 0.
|
336 |
-
"count":
|
337 |
"is_parallel": true,
|
338 |
-
"self": 0.
|
339 |
}
|
340 |
}
|
341 |
},
|
342 |
"_update_policy": {
|
343 |
-
"total":
|
344 |
-
"count":
|
345 |
"is_parallel": true,
|
346 |
-
"self":
|
347 |
"children": {
|
348 |
"TorchPPOOptimizer.update": {
|
349 |
-
"total":
|
350 |
-
"count":
|
351 |
"is_parallel": true,
|
352 |
-
"self":
|
353 |
}
|
354 |
}
|
355 |
}
|
@@ -360,14 +360,14 @@
|
|
360 |
}
|
361 |
},
|
362 |
"TrainerController._save_models": {
|
363 |
-
"total": 0.
|
364 |
"count": 1,
|
365 |
-
"self": 0.
|
366 |
"children": {
|
367 |
"RLTrainer._checkpoint": {
|
368 |
-
"total": 0.
|
369 |
"count": 1,
|
370 |
-
"self": 0.
|
371 |
}
|
372 |
}
|
373 |
}
|
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"SnowballTarget.Policy.Entropy.mean": {
|
5 |
+
"value": 0.9170640707015991,
|
6 |
+
"min": 0.9170640707015991,
|
7 |
+
"max": 2.860229730606079,
|
8 |
+
"count": 20
|
9 |
},
|
10 |
"SnowballTarget.Policy.Entropy.sum": {
|
11 |
+
"value": 8756.1279296875,
|
12 |
+
"min": 8756.1279296875,
|
13 |
+
"max": 29260.150390625,
|
14 |
+
"count": 20
|
15 |
},
|
16 |
"SnowballTarget.Step.mean": {
|
17 |
+
"value": 199984.0,
|
18 |
"min": 9952.0,
|
19 |
+
"max": 199984.0,
|
20 |
+
"count": 20
|
21 |
},
|
22 |
"SnowballTarget.Step.sum": {
|
23 |
+
"value": 199984.0,
|
24 |
"min": 9952.0,
|
25 |
+
"max": 199984.0,
|
26 |
+
"count": 20
|
27 |
},
|
28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
+
"value": 12.99020767211914,
|
30 |
+
"min": 0.326280802488327,
|
31 |
+
"max": 12.99020767211914,
|
32 |
+
"count": 20
|
33 |
},
|
34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
+
"value": 2533.090576171875,
|
36 |
+
"min": 63.2984733581543,
|
37 |
+
"max": 2638.36376953125,
|
38 |
+
"count": 20
|
39 |
},
|
40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
41 |
"value": 199.0,
|
42 |
"min": 199.0,
|
43 |
"max": 199.0,
|
44 |
+
"count": 20
|
45 |
},
|
46 |
"SnowballTarget.Environment.EpisodeLength.sum": {
|
47 |
+
"value": 8756.0,
|
48 |
"min": 8756.0,
|
49 |
"max": 10945.0,
|
50 |
+
"count": 20
|
51 |
},
|
52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
53 |
+
"value": 0.06786526505532617,
|
54 |
+
"min": 0.062182869404162316,
|
55 |
+
"max": 0.08021763855489839,
|
56 |
+
"count": 20
|
57 |
},
|
58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
59 |
+
"value": 0.2714610602213047,
|
60 |
+
"min": 0.24873147761664927,
|
61 |
+
"max": 0.36555384002970054,
|
62 |
+
"count": 20
|
63 |
},
|
64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
65 |
+
"value": 0.19483383474688903,
|
66 |
+
"min": 0.11548231221740043,
|
67 |
+
"max": 0.2769905658329234,
|
68 |
+
"count": 20
|
69 |
},
|
70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
71 |
+
"value": 0.7793353389875561,
|
72 |
+
"min": 0.46192924886960174,
|
73 |
+
"max": 1.3849528291646171,
|
74 |
+
"count": 20
|
75 |
},
|
76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
77 |
+
"value": 8.082097306000005e-06,
|
78 |
+
"min": 8.082097306000005e-06,
|
79 |
+
"max": 0.000291882002706,
|
80 |
+
"count": 20
|
81 |
},
|
82 |
"SnowballTarget.Policy.LearningRate.sum": {
|
83 |
+
"value": 3.232838922400002e-05,
|
84 |
+
"min": 3.232838922400002e-05,
|
85 |
+
"max": 0.00138516003828,
|
86 |
+
"count": 20
|
87 |
},
|
88 |
"SnowballTarget.Policy.Epsilon.mean": {
|
89 |
+
"value": 0.10269400000000001,
|
90 |
+
"min": 0.10269400000000001,
|
91 |
+
"max": 0.19729400000000002,
|
92 |
+
"count": 20
|
93 |
},
|
94 |
"SnowballTarget.Policy.Epsilon.sum": {
|
95 |
+
"value": 0.41077600000000003,
|
96 |
+
"min": 0.41077600000000003,
|
97 |
+
"max": 0.96172,
|
98 |
+
"count": 20
|
99 |
},
|
100 |
"SnowballTarget.Policy.Beta.mean": {
|
101 |
+
"value": 0.0001444306000000001,
|
102 |
+
"min": 0.0001444306000000001,
|
103 |
+
"max": 0.0048649706,
|
104 |
+
"count": 20
|
105 |
},
|
106 |
"SnowballTarget.Policy.Beta.sum": {
|
107 |
+
"value": 0.0005777224000000004,
|
108 |
+
"min": 0.0005777224000000004,
|
109 |
+
"max": 0.023089828,
|
110 |
+
"count": 20
|
111 |
},
|
112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
113 |
+
"value": 25.772727272727273,
|
114 |
+
"min": 3.4545454545454546,
|
115 |
+
"max": 25.772727272727273,
|
116 |
+
"count": 20
|
117 |
},
|
118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
119 |
+
"value": 1134.0,
|
120 |
+
"min": 152.0,
|
121 |
+
"max": 1406.0,
|
122 |
+
"count": 20
|
123 |
},
|
124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
125 |
+
"value": 25.772727272727273,
|
126 |
+
"min": 3.4545454545454546,
|
127 |
+
"max": 25.772727272727273,
|
128 |
+
"count": 20
|
129 |
},
|
130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
131 |
+
"value": 1134.0,
|
132 |
+
"min": 152.0,
|
133 |
+
"max": 1406.0,
|
134 |
+
"count": 20
|
135 |
},
|
136 |
"SnowballTarget.IsTraining.mean": {
|
137 |
"value": 1.0,
|
138 |
"min": 1.0,
|
139 |
"max": 1.0,
|
140 |
+
"count": 20
|
141 |
},
|
142 |
"SnowballTarget.IsTraining.sum": {
|
143 |
"value": 1.0,
|
144 |
"min": 1.0,
|
145 |
"max": 1.0,
|
146 |
+
"count": 20
|
147 |
}
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
+
"start_time_seconds": "1711017539",
|
152 |
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
|
153 |
+
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
|
154 |
"mlagents_version": "1.1.0.dev0",
|
155 |
"mlagents_envs_version": "1.1.0.dev0",
|
156 |
"communication_protocol_version": "1.5.0",
|
157 |
"pytorch_version": "2.2.1+cu121",
|
158 |
"numpy_version": "1.23.5",
|
159 |
+
"end_time_seconds": "1711017971"
|
160 |
},
|
161 |
+
"total": 432.23780170099985,
|
162 |
"count": 1,
|
163 |
+
"self": 0.43628886299984515,
|
164 |
"children": {
|
165 |
"run_training.setup": {
|
166 |
+
"total": 0.05209177799997633,
|
167 |
"count": 1,
|
168 |
+
"self": 0.05209177799997633
|
169 |
},
|
170 |
"TrainerController.start_learning": {
|
171 |
+
"total": 431.74942106000003,
|
172 |
"count": 1,
|
173 |
+
"self": 0.5362670520089523,
|
174 |
"children": {
|
175 |
"TrainerController._reset_env": {
|
176 |
+
"total": 1.960719116999826,
|
177 |
"count": 1,
|
178 |
+
"self": 1.960719116999826
|
179 |
},
|
180 |
"TrainerController.advance": {
|
181 |
+
"total": 429.1619950759912,
|
182 |
+
"count": 18198,
|
183 |
+
"self": 0.26251593598635736,
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
+
"total": 428.8994791400048,
|
187 |
+
"count": 18198,
|
188 |
+
"self": 274.3759014199686,
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
+
"total": 154.24752886000965,
|
192 |
+
"count": 18198,
|
193 |
+
"self": 1.4117804469999555,
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
+
"total": 152.8357484130097,
|
197 |
+
"count": 18198,
|
198 |
+
"self": 152.8357484130097
|
199 |
}
|
200 |
}
|
201 |
},
|
202 |
"workers": {
|
203 |
+
"total": 0.27604886002654894,
|
204 |
+
"count": 18198,
|
205 |
"self": 0.0,
|
206 |
"children": {
|
207 |
"worker_root": {
|
208 |
+
"total": 430.6149070170154,
|
209 |
+
"count": 18198,
|
210 |
"is_parallel": true,
|
211 |
+
"self": 215.42083069100227,
|
212 |
"children": {
|
213 |
"run_training.setup": {
|
214 |
"total": 0.0,
|
|
|
217 |
"self": 0.0,
|
218 |
"children": {
|
219 |
"steps_from_proto": {
|
220 |
+
"total": 0.0022657389999949373,
|
221 |
"count": 1,
|
222 |
"is_parallel": true,
|
223 |
+
"self": 0.0006678599997940182,
|
224 |
"children": {
|
225 |
"_process_rank_one_or_two_observation": {
|
226 |
+
"total": 0.0015978790002009191,
|
227 |
"count": 10,
|
228 |
"is_parallel": true,
|
229 |
+
"self": 0.0015978790002009191
|
230 |
}
|
231 |
}
|
232 |
},
|
233 |
"UnityEnvironment.step": {
|
234 |
+
"total": 0.03645421500004886,
|
235 |
"count": 1,
|
236 |
"is_parallel": true,
|
237 |
+
"self": 0.0006825499999649765,
|
238 |
"children": {
|
239 |
"UnityEnvironment._generate_step_input": {
|
240 |
+
"total": 0.0004073019999850658,
|
241 |
"count": 1,
|
242 |
"is_parallel": true,
|
243 |
+
"self": 0.0004073019999850658
|
244 |
},
|
245 |
"communicator.exchange": {
|
246 |
+
"total": 0.033227948000103424,
|
247 |
"count": 1,
|
248 |
"is_parallel": true,
|
249 |
+
"self": 0.033227948000103424
|
250 |
},
|
251 |
"steps_from_proto": {
|
252 |
+
"total": 0.002136414999995395,
|
253 |
"count": 1,
|
254 |
"is_parallel": true,
|
255 |
+
"self": 0.00041298300061498594,
|
256 |
"children": {
|
257 |
"_process_rank_one_or_two_observation": {
|
258 |
+
"total": 0.0017234319993804093,
|
259 |
"count": 10,
|
260 |
"is_parallel": true,
|
261 |
+
"self": 0.0017234319993804093
|
262 |
}
|
263 |
}
|
264 |
}
|
|
|
267 |
}
|
268 |
},
|
269 |
"UnityEnvironment.step": {
|
270 |
+
"total": 215.19407632601315,
|
271 |
+
"count": 18197,
|
272 |
"is_parallel": true,
|
273 |
+
"self": 10.024022665011444,
|
274 |
"children": {
|
275 |
"UnityEnvironment._generate_step_input": {
|
276 |
+
"total": 5.21538268302038,
|
277 |
+
"count": 18197,
|
278 |
"is_parallel": true,
|
279 |
+
"self": 5.21538268302038
|
280 |
},
|
281 |
"communicator.exchange": {
|
282 |
+
"total": 167.40767174697453,
|
283 |
+
"count": 18197,
|
284 |
"is_parallel": true,
|
285 |
+
"self": 167.40767174697453
|
286 |
},
|
287 |
"steps_from_proto": {
|
288 |
+
"total": 32.546999231006794,
|
289 |
+
"count": 18197,
|
290 |
"is_parallel": true,
|
291 |
+
"self": 6.064365135041953,
|
292 |
"children": {
|
293 |
"_process_rank_one_or_two_observation": {
|
294 |
+
"total": 26.48263409596484,
|
295 |
+
"count": 181970,
|
296 |
"is_parallel": true,
|
297 |
+
"self": 26.48263409596484
|
298 |
}
|
299 |
}
|
300 |
}
|
|
|
309 |
}
|
310 |
},
|
311 |
"trainer_threads": {
|
312 |
+
"total": 0.00012526899990916718,
|
313 |
"count": 1,
|
314 |
+
"self": 0.00012526899990916718,
|
315 |
"children": {
|
316 |
"thread_root": {
|
317 |
"total": 0.0,
|
|
|
320 |
"self": 0.0,
|
321 |
"children": {
|
322 |
"trainer_advance": {
|
323 |
+
"total": 423.68849228009753,
|
324 |
+
"count": 659375,
|
325 |
"is_parallel": true,
|
326 |
+
"self": 14.235416164080561,
|
327 |
"children": {
|
328 |
"process_trajectory": {
|
329 |
+
"total": 233.49233048901806,
|
330 |
+
"count": 659375,
|
331 |
"is_parallel": true,
|
332 |
+
"self": 232.82248147301766,
|
333 |
"children": {
|
334 |
"RLTrainer._checkpoint": {
|
335 |
+
"total": 0.6698490160003985,
|
336 |
+
"count": 4,
|
337 |
"is_parallel": true,
|
338 |
+
"self": 0.6698490160003985
|
339 |
}
|
340 |
}
|
341 |
},
|
342 |
"_update_policy": {
|
343 |
+
"total": 175.96074562699891,
|
344 |
+
"count": 90,
|
345 |
"is_parallel": true,
|
346 |
+
"self": 50.79041540399794,
|
347 |
"children": {
|
348 |
"TorchPPOOptimizer.update": {
|
349 |
+
"total": 125.17033022300097,
|
350 |
+
"count": 4587,
|
351 |
"is_parallel": true,
|
352 |
+
"self": 125.17033022300097
|
353 |
}
|
354 |
}
|
355 |
}
|
|
|
360 |
}
|
361 |
},
|
362 |
"TrainerController._save_models": {
|
363 |
+
"total": 0.09031454600017241,
|
364 |
"count": 1,
|
365 |
+
"self": 0.0010352740000598715,
|
366 |
"children": {
|
367 |
"RLTrainer._checkpoint": {
|
368 |
+
"total": 0.08927927200011254,
|
369 |
"count": 1,
|
370 |
+
"self": 0.08927927200011254
|
371 |
}
|
372 |
}
|
373 |
}
|
run_logs/training_status.json
CHANGED
@@ -3,39 +3,57 @@
|
|
3 |
"checkpoints": [
|
4 |
{
|
5 |
"steps": 49936,
|
6 |
-
"file_path": "results/
|
7 |
-
"reward":
|
8 |
-
"creation_time":
|
9 |
"auxillary_file_paths": [
|
10 |
-
"results/
|
11 |
]
|
12 |
},
|
13 |
{
|
14 |
"steps": 99960,
|
15 |
-
"file_path": "results/
|
16 |
-
"reward":
|
17 |
-
"creation_time":
|
18 |
"auxillary_file_paths": [
|
19 |
-
"results/
|
20 |
]
|
21 |
},
|
22 |
{
|
23 |
-
"steps":
|
24 |
-
"file_path": "results/
|
25 |
-
"reward":
|
26 |
-
"creation_time":
|
27 |
"auxillary_file_paths": [
|
28 |
-
"results/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
]
|
30 |
}
|
31 |
],
|
32 |
"final_checkpoint": {
|
33 |
-
"steps":
|
34 |
-
"file_path": "results/
|
35 |
-
"reward":
|
36 |
-
"creation_time":
|
37 |
"auxillary_file_paths": [
|
38 |
-
"results/
|
39 |
]
|
40 |
}
|
41 |
},
|
|
|
3 |
"checkpoints": [
|
4 |
{
|
5 |
"steps": 49936,
|
6 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
|
7 |
+
"reward": 13.909090909090908,
|
8 |
+
"creation_time": 1711017649.3470476,
|
9 |
"auxillary_file_paths": [
|
10 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
|
11 |
]
|
12 |
},
|
13 |
{
|
14 |
"steps": 99960,
|
15 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
|
16 |
+
"reward": 21.0,
|
17 |
+
"creation_time": 1711017756.769436,
|
18 |
"auxillary_file_paths": [
|
19 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
|
20 |
]
|
21 |
},
|
22 |
{
|
23 |
+
"steps": 149984,
|
24 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
|
25 |
+
"reward": 25.363636363636363,
|
26 |
+
"creation_time": 1711017864.986829,
|
27 |
"auxillary_file_paths": [
|
28 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
|
29 |
+
]
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"steps": 199984,
|
33 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
|
34 |
+
"reward": 26.09090909090909,
|
35 |
+
"creation_time": 1711017970.849175,
|
36 |
+
"auxillary_file_paths": [
|
37 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
|
38 |
+
]
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"steps": 200112,
|
42 |
+
"file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
|
43 |
+
"reward": 26.09090909090909,
|
44 |
+
"creation_time": 1711017970.9633875,
|
45 |
+
"auxillary_file_paths": [
|
46 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
|
47 |
]
|
48 |
}
|
49 |
],
|
50 |
"final_checkpoint": {
|
51 |
+
"steps": 200112,
|
52 |
+
"file_path": "results/SnowballTarget2/SnowballTarget.onnx",
|
53 |
+
"reward": 26.09090909090909,
|
54 |
+
"creation_time": 1711017970.9633875,
|
55 |
"auxillary_file_paths": [
|
56 |
+
"results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
|
57 |
]
|
58 |
}
|
59 |
},
|