First Commit
Browse files- SnowballTarget.onnx +1 -1
- SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-249984.onnx} +1 -1
- SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-249984.pt} +1 -1
- SnowballTarget/SnowballTarget-299944.onnx +3 -0
- SnowballTarget/SnowballTarget-299944.pt +3 -0
- SnowballTarget/SnowballTarget-349968.onnx +3 -0
- SnowballTarget/SnowballTarget-349968.pt +3 -0
- SnowballTarget/SnowballTarget-399968.onnx +3 -0
- SnowballTarget/SnowballTarget-399968.pt +3 -0
- SnowballTarget/SnowballTarget-400224.onnx +3 -0
- SnowballTarget/SnowballTarget-400224.pt +3 -0
- SnowballTarget/checkpoint.pt +1 -1
- SnowballTarget/events.out.tfevents.1679878826.3bb84cbeccac.7343.0 +3 -0
- SnowballTarget/events.out.tfevents.1679878877.3bb84cbeccac.7628.0 +3 -0
- config.json +1 -1
- configuration.yaml +2 -2
- run_logs/Player-0.log +15 -18
- run_logs/timers.json +135 -135
- run_logs/training_status.json +58 -13
SnowballTarget.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 646532
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:717098b6d3c6caef564da5b2633636772400e9bec5148b8b24eb7627e4fec9c4
|
3 |
size 646532
|
SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-249984.onnx}
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 646532
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b11a58dd63fc44c77ee111bffafb94931cf330aded2747a32c91732d8e3ab8b
|
3 |
size 646532
|
SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-249984.pt}
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3843200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39d27286ef73242cc6e47f70a450f4b016a61a83fabd88da118f33287493f2ed
|
3 |
size 3843200
|
SnowballTarget/SnowballTarget-299944.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c6d111fce237ceeb4d64ddddbec803d4a058ae12f7c9d5d2c8c3bbf0b4783b0
|
3 |
+
size 646532
|
SnowballTarget/SnowballTarget-299944.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f797c2c0e48bfcd143ac98e7c55e2ccefddf2502b38e62972cdf57ddb8aac36b
|
3 |
+
size 3843200
|
SnowballTarget/SnowballTarget-349968.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de7829a9e0d660450b125ae9338e579d8642ad514885e084375fbcf19f467715
|
3 |
+
size 646532
|
SnowballTarget/SnowballTarget-349968.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46a4d23df970a1ac27b8891163c271b626a19e0b948e5aaece1d37dd15a8e8bc
|
3 |
+
size 3843200
|
SnowballTarget/SnowballTarget-399968.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:717098b6d3c6caef564da5b2633636772400e9bec5148b8b24eb7627e4fec9c4
|
3 |
+
size 646532
|
SnowballTarget/SnowballTarget-399968.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aa32653dc96ee3c39f6b472d3dbee1a8698e272e55a648db8af58adbd5b32c5
|
3 |
+
size 3843200
|
SnowballTarget/SnowballTarget-400224.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:717098b6d3c6caef564da5b2633636772400e9bec5148b8b24eb7627e4fec9c4
|
3 |
+
size 646532
|
SnowballTarget/SnowballTarget-400224.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e026268f954f44fc85d6f43a564cdd0e81a31ea7fe3950e50bfcdaaecb535115
|
3 |
+
size 3843200
|
SnowballTarget/checkpoint.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3843200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e026268f954f44fc85d6f43a564cdd0e81a31ea7fe3950e50bfcdaaecb535115
|
3 |
size 3843200
|
SnowballTarget/events.out.tfevents.1679878826.3bb84cbeccac.7343.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a6b65d54aa10eb2fb10366fe90faef72f53651c57fc4bfd4541bfb11ed1de37
|
3 |
+
size 1066
|
SnowballTarget/events.out.tfevents.1679878877.3bb84cbeccac.7628.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2921210c02ec13d501b84cb150362c90d7b94df2f03ac382de735091b49d6151
|
3 |
+
size 17394
|
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": 400000, "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": true, "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
|
@@ -67,7 +67,7 @@ checkpoint_settings:
|
|
67 |
run_id: SnowballTarget1
|
68 |
initialize_from: null
|
69 |
load_model: false
|
70 |
-
resume:
|
71 |
force: false
|
72 |
train_model: false
|
73 |
inference: false
|
|
|
38 |
init_path: null
|
39 |
keep_checkpoints: 10
|
40 |
even_checkpoints: false
|
41 |
+
max_steps: 400000
|
42 |
time_horizon: 64
|
43 |
summary_freq: 10000
|
44 |
threaded: true
|
|
|
67 |
run_id: SnowballTarget1
|
68 |
initialize_from: null
|
69 |
load_model: false
|
70 |
+
resume: true
|
71 |
force: false
|
72 |
train_model: false
|
73 |
inference: false
|
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:2642:(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.
|
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:
|
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.
|
@@ -53,7 +50,7 @@ Memory Statistics:
|
|
53 |
[ALLOC_TEMP_TLS] TLS Allocator
|
54 |
StackAllocators :
|
55 |
[ALLOC_TEMP_MAIN]
|
56 |
-
Peak usage frame count: [8.0 KB-16.0 KB]:
|
57 |
Initial Block Size 4.0 MB
|
58 |
Current Block Size 4.0 MB
|
59 |
Peak Allocated Bytes 2.0 MB
|
@@ -169,22 +166,22 @@ Memory Statistics:
|
|
169 |
Peak Allocated Bytes 0 B
|
170 |
Overflow Count 0
|
171 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
172 |
-
Peak main deferred allocation count
|
173 |
[ALLOC_BUCKET]
|
174 |
Large Block size 4.0 MB
|
175 |
Used Block count 1
|
176 |
Peak Allocated bytes 1.0 MB
|
177 |
[ALLOC_DEFAULT_MAIN]
|
178 |
-
Peak usage frame count: [4.0 MB-8.0 MB]:
|
179 |
Requested Block Size 16.0 MB
|
180 |
Peak Block count 1
|
181 |
-
Peak Allocated memory 6.
|
182 |
Peak Large allocation bytes 0 B
|
183 |
[ALLOC_DEFAULT_THREAD]
|
184 |
-
Peak usage frame count: [16.0 MB-32.0 MB]:
|
185 |
Requested Block Size 16.0 MB
|
186 |
Peak Block count 1
|
187 |
-
Peak Allocated memory 17.
|
188 |
Peak Large allocation bytes 16.0 MB
|
189 |
[ALLOC_TEMP_JOB_1_FRAME]
|
190 |
Initial Block Size 2.0 MB
|
@@ -213,13 +210,13 @@ 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]:
|
217 |
Requested Block Size 16.0 MB
|
218 |
Peak Block count 1
|
219 |
-
Peak Allocated memory
|
220 |
Peak Large allocation bytes 0 B
|
221 |
[ALLOC_GFX_THREAD]
|
222 |
-
Peak usage frame count: [32.0 KB-64.0 KB]:
|
223 |
Requested Block Size 16.0 MB
|
224 |
Peak Block count 1
|
225 |
Peak Allocated memory 39.6 KB
|
@@ -231,13 +228,13 @@ Memory Statistics:
|
|
231 |
Used Block count 1
|
232 |
Peak Allocated bytes 1.0 MB
|
233 |
[ALLOC_CACHEOBJECTS_MAIN]
|
234 |
-
Peak usage frame count: [0.5 MB-1.0 MB]:
|
235 |
Requested Block Size 4.0 MB
|
236 |
Peak Block count 1
|
237 |
Peak Allocated memory 0.6 MB
|
238 |
Peak Large allocation bytes 0 B
|
239 |
[ALLOC_CACHEOBJECTS_THREAD]
|
240 |
-
Peak usage frame count: [0.5 MB-1.0 MB]:
|
241 |
Requested Block Size 4.0 MB
|
242 |
Peak Block count 1
|
243 |
Peak Allocated memory 2.2 MB
|
@@ -249,13 +246,13 @@ Memory Statistics:
|
|
249 |
Used Block count 1
|
250 |
Peak Allocated bytes 1.0 MB
|
251 |
[ALLOC_TYPETREE_MAIN]
|
252 |
-
Peak usage frame count: [0-1.0 KB]:
|
253 |
Requested Block Size 2.0 MB
|
254 |
Peak Block count 1
|
255 |
Peak Allocated memory 1.0 KB
|
256 |
Peak Large allocation bytes 0 B
|
257 |
[ALLOC_TYPETREE_THREAD]
|
258 |
-
Peak usage frame count: [1.0 KB-2.0 KB]:
|
259 |
Requested Block Size 2.0 MB
|
260 |
Peak Block count 1
|
261 |
Peak Allocated memory 1.7 KB
|
|
|
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 0.098 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: 0.826367 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]: 5374 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 32
|
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]: 5466 frames
|
176 |
Requested Block Size 16.0 MB
|
177 |
Peak Block count 1
|
178 |
+
Peak Allocated memory 6.8 MB
|
179 |
Peak Large allocation bytes 0 B
|
180 |
[ALLOC_DEFAULT_THREAD]
|
181 |
+
Peak usage frame count: [16.0 MB-32.0 MB]: 5466 frames
|
182 |
Requested Block Size 16.0 MB
|
183 |
Peak Block count 1
|
184 |
+
Peak Allocated memory 17.7 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]: 5304 frames, [64.0 KB-128.0 KB]: 162 frames
|
214 |
Requested Block Size 16.0 MB
|
215 |
Peak Block count 1
|
216 |
+
Peak Allocated memory 66.8 KB
|
217 |
Peak Large allocation bytes 0 B
|
218 |
[ALLOC_GFX_THREAD]
|
219 |
+
Peak usage frame count: [32.0 KB-64.0 KB]: 5466 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]: 5466 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]: 5465 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]: 5466 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]: 5466 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
@@ -2,39 +2,39 @@
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"SnowballTarget.Policy.Entropy.mean": {
|
5 |
-
"value":
|
6 |
-
"min":
|
7 |
-
"max":
|
8 |
"count": 20
|
9 |
},
|
10 |
"SnowballTarget.Policy.Entropy.sum": {
|
11 |
-
"value":
|
12 |
-
"min":
|
13 |
-
"max":
|
14 |
"count": 20
|
15 |
},
|
16 |
"SnowballTarget.Step.mean": {
|
17 |
-
"value":
|
18 |
-
"min":
|
19 |
-
"max":
|
20 |
"count": 20
|
21 |
},
|
22 |
"SnowballTarget.Step.sum": {
|
23 |
-
"value":
|
24 |
-
"min":
|
25 |
-
"max":
|
26 |
"count": 20
|
27 |
},
|
28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
-
"value":
|
30 |
-
"min":
|
31 |
-
"max":
|
32 |
"count": 20
|
33 |
},
|
34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
-
"value":
|
36 |
-
"min":
|
37 |
-
"max":
|
38 |
"count": 20
|
39 |
},
|
40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
@@ -50,87 +50,87 @@
|
|
50 |
"count": 20
|
51 |
},
|
52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
53 |
-
"value": 0.
|
54 |
-
"min": 0.
|
55 |
-
"max": 0.
|
56 |
"count": 20
|
57 |
},
|
58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
59 |
-
"value": 0.
|
60 |
-
"min": 0.
|
61 |
-
"max": 0.
|
62 |
"count": 20
|
63 |
},
|
64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
65 |
-
"value": 0.
|
66 |
-
"min": 0.
|
67 |
-
"max": 0.
|
68 |
"count": 20
|
69 |
},
|
70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
71 |
-
"value": 0.
|
72 |
-
"min": 0.
|
73 |
-
"max": 1.
|
74 |
"count": 20
|
75 |
},
|
76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
77 |
-
"value":
|
78 |
-
"min":
|
79 |
-
"max": 0.
|
80 |
"count": 20
|
81 |
},
|
82 |
"SnowballTarget.Policy.LearningRate.sum": {
|
83 |
-
"value":
|
84 |
-
"min":
|
85 |
-
"max": 0.
|
86 |
"count": 20
|
87 |
},
|
88 |
"SnowballTarget.Policy.Epsilon.mean": {
|
89 |
-
"value": 0.
|
90 |
-
"min": 0.
|
91 |
-
"max": 0.
|
92 |
"count": 20
|
93 |
},
|
94 |
"SnowballTarget.Policy.Epsilon.sum": {
|
95 |
-
"value": 0.
|
96 |
-
"min": 0.
|
97 |
-
"max": 0.
|
98 |
"count": 20
|
99 |
},
|
100 |
"SnowballTarget.Policy.Beta.mean": {
|
101 |
-
"value":
|
102 |
-
"min":
|
103 |
-
"max": 0.
|
104 |
"count": 20
|
105 |
},
|
106 |
"SnowballTarget.Policy.Beta.sum": {
|
107 |
-
"value": 0.
|
108 |
-
"min": 0.
|
109 |
-
"max": 0.
|
110 |
"count": 20
|
111 |
},
|
112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
113 |
-
"value":
|
114 |
-
"min":
|
115 |
-
"max":
|
116 |
"count": 20
|
117 |
},
|
118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
119 |
-
"value":
|
120 |
-
"min":
|
121 |
-
"max":
|
122 |
"count": 20
|
123 |
},
|
124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
125 |
-
"value":
|
126 |
-
"min":
|
127 |
-
"max":
|
128 |
"count": 20
|
129 |
},
|
130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
131 |
-
"value":
|
132 |
-
"min":
|
133 |
-
"max":
|
134 |
"count": 20
|
135 |
},
|
136 |
"SnowballTarget.IsTraining.mean": {
|
@@ -148,67 +148,67 @@
|
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
-
"start_time_seconds": "
|
152 |
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
|
153 |
-
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
|
154 |
"mlagents_version": "0.31.0.dev0",
|
155 |
"mlagents_envs_version": "0.31.0.dev0",
|
156 |
"communication_protocol_version": "1.5.0",
|
157 |
"pytorch_version": "1.11.0+cu102",
|
158 |
"numpy_version": "1.21.2",
|
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": 108.
|
197 |
-
"count":
|
198 |
-
"self": 108.
|
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": 254.
|
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": 42.
|
289 |
-
"count":
|
290 |
"is_parallel": true,
|
291 |
-
"self": 8.
|
292 |
"children": {
|
293 |
"_process_rank_one_or_two_observation": {
|
294 |
-
"total": 33.
|
295 |
-
"count":
|
296 |
"is_parallel": true,
|
297 |
-
"self": 33.
|
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": 15.
|
327 |
"children": {
|
328 |
"process_trajectory": {
|
329 |
-
"total":
|
330 |
-
"count":
|
331 |
"is_parallel": true,
|
332 |
-
"self":
|
333 |
"children": {
|
334 |
"RLTrainer._checkpoint": {
|
335 |
-
"total":
|
336 |
"count": 4,
|
337 |
"is_parallel": true,
|
338 |
-
"self":
|
339 |
}
|
340 |
}
|
341 |
},
|
342 |
"_update_policy": {
|
343 |
-
"total":
|
344 |
"count": 90,
|
345 |
"is_parallel": true,
|
346 |
-
"self": 83.
|
347 |
"children": {
|
348 |
"TorchPPOOptimizer.update": {
|
349 |
-
"total":
|
350 |
"count": 4587,
|
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": 0.7914053201675415,
|
6 |
+
"min": 0.7395239472389221,
|
7 |
+
"max": 1.0724937915802002,
|
8 |
"count": 20
|
9 |
},
|
10 |
"SnowballTarget.Policy.Entropy.sum": {
|
11 |
+
"value": 8061.2548828125,
|
12 |
+
"min": 7238.7158203125,
|
13 |
+
"max": 10983.4091796875,
|
14 |
"count": 20
|
15 |
},
|
16 |
"SnowballTarget.Step.mean": {
|
17 |
+
"value": 399968.0,
|
18 |
+
"min": 209936.0,
|
19 |
+
"max": 399968.0,
|
20 |
"count": 20
|
21 |
},
|
22 |
"SnowballTarget.Step.sum": {
|
23 |
+
"value": 399968.0,
|
24 |
+
"min": 209936.0,
|
25 |
+
"max": 399968.0,
|
26 |
"count": 20
|
27 |
},
|
28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
29 |
+
"value": 13.424694061279297,
|
30 |
+
"min": 12.863568305969238,
|
31 |
+
"max": 13.596199989318848,
|
32 |
"count": 20
|
33 |
},
|
34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
35 |
+
"value": 2617.8154296875,
|
36 |
+
"min": 2469.80517578125,
|
37 |
+
"max": 2767.04541015625,
|
38 |
"count": 20
|
39 |
},
|
40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
|
|
50 |
"count": 20
|
51 |
},
|
52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
53 |
+
"value": 0.06790241125261175,
|
54 |
+
"min": 0.06417496013826024,
|
55 |
+
"max": 0.07435267957253197,
|
56 |
"count": 20
|
57 |
},
|
58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
59 |
+
"value": 0.271609645010447,
|
60 |
+
"min": 0.25669984055304096,
|
61 |
+
"max": 0.37176339786265983,
|
62 |
"count": 20
|
63 |
},
|
64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
65 |
+
"value": 0.19967366433611103,
|
66 |
+
"min": 0.16358210274255744,
|
67 |
+
"max": 0.2097026512611146,
|
68 |
"count": 20
|
69 |
},
|
70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
71 |
+
"value": 0.7986946573444441,
|
72 |
+
"min": 0.6543284109702298,
|
73 |
+
"max": 1.048513256305573,
|
74 |
"count": 20
|
75 |
},
|
76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
77 |
+
"value": 3.957098681000002e-06,
|
78 |
+
"min": 3.957098681000002e-06,
|
79 |
+
"max": 0.000145857051381,
|
80 |
"count": 20
|
81 |
},
|
82 |
"SnowballTarget.Policy.LearningRate.sum": {
|
83 |
+
"value": 1.582839472400001e-05,
|
84 |
+
"min": 1.582839472400001e-05,
|
85 |
+
"max": 0.00069216026928,
|
86 |
"count": 20
|
87 |
},
|
88 |
"SnowballTarget.Policy.Epsilon.mean": {
|
89 |
+
"value": 0.101319,
|
90 |
+
"min": 0.101319,
|
91 |
+
"max": 0.14861900000000003,
|
92 |
"count": 20
|
93 |
},
|
94 |
"SnowballTarget.Policy.Epsilon.sum": {
|
95 |
+
"value": 0.405276,
|
96 |
+
"min": 0.405276,
|
97 |
+
"max": 0.73072,
|
98 |
"count": 20
|
99 |
},
|
100 |
"SnowballTarget.Policy.Beta.mean": {
|
101 |
+
"value": 7.581810000000006e-05,
|
102 |
+
"min": 7.581810000000006e-05,
|
103 |
+
"max": 0.0024360881000000003,
|
104 |
"count": 20
|
105 |
},
|
106 |
"SnowballTarget.Policy.Beta.sum": {
|
107 |
+
"value": 0.00030327240000000024,
|
108 |
+
"min": 0.00030327240000000024,
|
109 |
+
"max": 0.011562928000000002,
|
110 |
"count": 20
|
111 |
},
|
112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
113 |
+
"value": 26.136363636363637,
|
114 |
+
"min": 25.40909090909091,
|
115 |
+
"max": 26.636363636363637,
|
116 |
"count": 20
|
117 |
},
|
118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
119 |
+
"value": 1150.0,
|
120 |
+
"min": 1118.0,
|
121 |
+
"max": 1465.0,
|
122 |
"count": 20
|
123 |
},
|
124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
125 |
+
"value": 26.136363636363637,
|
126 |
+
"min": 25.40909090909091,
|
127 |
+
"max": 26.636363636363637,
|
128 |
"count": 20
|
129 |
},
|
130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
131 |
+
"value": 1150.0,
|
132 |
+
"min": 1118.0,
|
133 |
+
"max": 1465.0,
|
134 |
"count": 20
|
135 |
},
|
136 |
"SnowballTarget.IsTraining.mean": {
|
|
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
+
"start_time_seconds": "1679878874",
|
152 |
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
|
153 |
+
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
|
154 |
"mlagents_version": "0.31.0.dev0",
|
155 |
"mlagents_envs_version": "0.31.0.dev0",
|
156 |
"communication_protocol_version": "1.5.0",
|
157 |
"pytorch_version": "1.11.0+cu102",
|
158 |
"numpy_version": "1.21.2",
|
159 |
+
"end_time_seconds": "1679879452"
|
160 |
},
|
161 |
+
"total": 578.5950579900002,
|
162 |
"count": 1,
|
163 |
+
"self": 0.7875139050004236,
|
164 |
"children": {
|
165 |
"run_training.setup": {
|
166 |
+
"total": 0.12787517399988246,
|
167 |
"count": 1,
|
168 |
+
"self": 0.12787517399988246
|
169 |
},
|
170 |
"TrainerController.start_learning": {
|
171 |
+
"total": 577.6796689109999,
|
172 |
"count": 1,
|
173 |
+
"self": 0.8763217719767908,
|
174 |
"children": {
|
175 |
"TrainerController._reset_env": {
|
176 |
+
"total": 3.541371915999889,
|
177 |
"count": 1,
|
178 |
+
"self": 3.541371915999889
|
179 |
},
|
180 |
"TrainerController.advance": {
|
181 |
+
"total": 573.0206384500232,
|
182 |
+
"count": 18217,
|
183 |
+
"self": 0.4247037960265061,
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
+
"total": 572.5959346539967,
|
187 |
+
"count": 18217,
|
188 |
+
"self": 461.32161100900294,
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
+
"total": 110.86947813401434,
|
192 |
+
"count": 18217,
|
193 |
+
"self": 2.5469452100292074,
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
+
"total": 108.32253292398514,
|
197 |
+
"count": 18217,
|
198 |
+
"self": 108.32253292398514
|
199 |
}
|
200 |
}
|
201 |
},
|
202 |
"workers": {
|
203 |
+
"total": 0.4048455109793849,
|
204 |
+
"count": 18217,
|
205 |
"self": 0.0,
|
206 |
"children": {
|
207 |
"worker_root": {
|
208 |
+
"total": 575.5761968960053,
|
209 |
+
"count": 18217,
|
210 |
"is_parallel": true,
|
211 |
+
"self": 254.10359240097273,
|
212 |
"children": {
|
213 |
"run_training.setup": {
|
214 |
"total": 0.0,
|
|
|
217 |
"self": 0.0,
|
218 |
"children": {
|
219 |
"steps_from_proto": {
|
220 |
+
"total": 0.002231082999969658,
|
221 |
"count": 1,
|
222 |
"is_parallel": true,
|
223 |
+
"self": 0.0006481899997652363,
|
224 |
"children": {
|
225 |
"_process_rank_one_or_two_observation": {
|
226 |
+
"total": 0.0015828930002044217,
|
227 |
"count": 10,
|
228 |
"is_parallel": true,
|
229 |
+
"self": 0.0015828930002044217
|
230 |
}
|
231 |
}
|
232 |
},
|
233 |
"UnityEnvironment.step": {
|
234 |
+
"total": 0.050761229000045205,
|
235 |
"count": 1,
|
236 |
"is_parallel": true,
|
237 |
+
"self": 0.0006805990001339524,
|
238 |
"children": {
|
239 |
"UnityEnvironment._generate_step_input": {
|
240 |
+
"total": 0.0003413889999137609,
|
241 |
"count": 1,
|
242 |
"is_parallel": true,
|
243 |
+
"self": 0.0003413889999137609
|
244 |
},
|
245 |
"communicator.exchange": {
|
246 |
+
"total": 0.04752009300000282,
|
247 |
"count": 1,
|
248 |
"is_parallel": true,
|
249 |
+
"self": 0.04752009300000282
|
250 |
},
|
251 |
"steps_from_proto": {
|
252 |
+
"total": 0.002219147999994675,
|
253 |
"count": 1,
|
254 |
"is_parallel": true,
|
255 |
+
"self": 0.0004505099996094941,
|
256 |
"children": {
|
257 |
"_process_rank_one_or_two_observation": {
|
258 |
+
"total": 0.001768638000385181,
|
259 |
"count": 10,
|
260 |
"is_parallel": true,
|
261 |
+
"self": 0.001768638000385181
|
262 |
}
|
263 |
}
|
264 |
}
|
|
|
267 |
}
|
268 |
},
|
269 |
"UnityEnvironment.step": {
|
270 |
+
"total": 321.47260449503256,
|
271 |
+
"count": 18216,
|
272 |
"is_parallel": true,
|
273 |
+
"self": 12.923220877001768,
|
274 |
"children": {
|
275 |
"UnityEnvironment._generate_step_input": {
|
276 |
+
"total": 6.977096945038056,
|
277 |
+
"count": 18216,
|
278 |
"is_parallel": true,
|
279 |
+
"self": 6.977096945038056
|
280 |
},
|
281 |
"communicator.exchange": {
|
282 |
+
"total": 259.1599640960078,
|
283 |
+
"count": 18216,
|
284 |
"is_parallel": true,
|
285 |
+
"self": 259.1599640960078
|
286 |
},
|
287 |
"steps_from_proto": {
|
288 |
+
"total": 42.412322576984934,
|
289 |
+
"count": 18216,
|
290 |
"is_parallel": true,
|
291 |
+
"self": 8.915250689944742,
|
292 |
"children": {
|
293 |
"_process_rank_one_or_two_observation": {
|
294 |
+
"total": 33.49707188704019,
|
295 |
+
"count": 182160,
|
296 |
"is_parallel": true,
|
297 |
+
"self": 33.49707188704019
|
298 |
}
|
299 |
}
|
300 |
}
|
|
|
309 |
}
|
310 |
},
|
311 |
"trainer_threads": {
|
312 |
+
"total": 0.00034158600010414375,
|
313 |
"count": 1,
|
314 |
+
"self": 0.00034158600010414375,
|
315 |
"children": {
|
316 |
"thread_root": {
|
317 |
"total": 0.0,
|
|
|
320 |
"self": 0.0,
|
321 |
"children": {
|
322 |
"trainer_advance": {
|
323 |
+
"total": 567.4594976457272,
|
324 |
+
"count": 645045,
|
325 |
"is_parallel": true,
|
326 |
+
"self": 15.776210985784019,
|
327 |
"children": {
|
328 |
"process_trajectory": {
|
329 |
+
"total": 305.99285114094437,
|
330 |
+
"count": 645045,
|
331 |
"is_parallel": true,
|
332 |
+
"self": 304.0477899739442,
|
333 |
"children": {
|
334 |
"RLTrainer._checkpoint": {
|
335 |
+
"total": 1.9450611670001763,
|
336 |
"count": 4,
|
337 |
"is_parallel": true,
|
338 |
+
"self": 1.9450611670001763
|
339 |
}
|
340 |
}
|
341 |
},
|
342 |
"_update_policy": {
|
343 |
+
"total": 245.6904355189988,
|
344 |
"count": 90,
|
345 |
"is_parallel": true,
|
346 |
+
"self": 83.20750559399994,
|
347 |
"children": {
|
348 |
"TorchPPOOptimizer.update": {
|
349 |
+
"total": 162.48292992499887,
|
350 |
"count": 4587,
|
351 |
"is_parallel": true,
|
352 |
+
"self": 162.48292992499887
|
353 |
}
|
354 |
}
|
355 |
}
|
|
|
360 |
}
|
361 |
},
|
362 |
"TrainerController._save_models": {
|
363 |
+
"total": 0.24099518699995315,
|
364 |
"count": 1,
|
365 |
+
"self": 0.0031808020003154525,
|
366 |
"children": {
|
367 |
"RLTrainer._checkpoint": {
|
368 |
+
"total": 0.2378143849996377,
|
369 |
"count": 1,
|
370 |
+
"self": 0.2378143849996377
|
371 |
}
|
372 |
}
|
373 |
}
|
run_logs/training_status.json
CHANGED
@@ -1,15 +1,6 @@
|
|
1 |
{
|
2 |
"SnowballTarget": {
|
3 |
"checkpoints": [
|
4 |
-
{
|
5 |
-
"steps": 49936,
|
6 |
-
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
|
7 |
-
"reward": 12.909090909090908,
|
8 |
-
"creation_time": 1679877937.221222,
|
9 |
-
"auxillary_file_paths": [
|
10 |
-
"results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
|
11 |
-
]
|
12 |
-
},
|
13 |
{
|
14 |
"steps": 99960,
|
15 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
|
@@ -45,15 +36,69 @@
|
|
45 |
"auxillary_file_paths": [
|
46 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
47 |
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"final_checkpoint": {
|
51 |
-
"steps":
|
52 |
"file_path": "results/SnowballTarget1/SnowballTarget.onnx",
|
53 |
-
"reward": 25.
|
54 |
-
"creation_time":
|
55 |
"auxillary_file_paths": [
|
56 |
-
"results/SnowballTarget1/SnowballTarget/SnowballTarget-
|
57 |
]
|
58 |
}
|
59 |
},
|
|
|
1 |
{
|
2 |
"SnowballTarget": {
|
3 |
"checkpoints": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
{
|
5 |
"steps": 99960,
|
6 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
|
|
|
36 |
"auxillary_file_paths": [
|
37 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
38 |
]
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"steps": 200112,
|
42 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
|
43 |
+
"reward": null,
|
44 |
+
"creation_time": 1679878826.420901,
|
45 |
+
"auxillary_file_paths": [
|
46 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
47 |
+
]
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"steps": 249984,
|
51 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
|
52 |
+
"reward": 26.545454545454547,
|
53 |
+
"creation_time": 1679879023.2624993,
|
54 |
+
"auxillary_file_paths": [
|
55 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
|
56 |
+
]
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"steps": 299944,
|
60 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
|
61 |
+
"reward": 26.0,
|
62 |
+
"creation_time": 1679879166.2183087,
|
63 |
+
"auxillary_file_paths": [
|
64 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
|
65 |
+
]
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"steps": 349968,
|
69 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
|
70 |
+
"reward": 25.818181818181817,
|
71 |
+
"creation_time": 1679879310.2593782,
|
72 |
+
"auxillary_file_paths": [
|
73 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
|
74 |
+
]
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"steps": 399968,
|
78 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
|
79 |
+
"reward": 25.181818181818183,
|
80 |
+
"creation_time": 1679879451.8105986,
|
81 |
+
"auxillary_file_paths": [
|
82 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
|
83 |
+
]
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"steps": 400224,
|
87 |
+
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.onnx",
|
88 |
+
"reward": 25.181818181818183,
|
89 |
+
"creation_time": 1679879452.1035855,
|
90 |
+
"auxillary_file_paths": [
|
91 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.pt"
|
92 |
+
]
|
93 |
}
|
94 |
],
|
95 |
"final_checkpoint": {
|
96 |
+
"steps": 400224,
|
97 |
"file_path": "results/SnowballTarget1/SnowballTarget.onnx",
|
98 |
+
"reward": 25.181818181818183,
|
99 |
+
"creation_time": 1679879452.1035855,
|
100 |
"auxillary_file_paths": [
|
101 |
+
"results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.pt"
|
102 |
]
|
103 |
}
|
104 |
},
|