max_steps = 5e7
Browse files- SoccerTwos.onnx +1 -1
- SoccerTwos/SoccerTwos-48499998.onnx +3 -0
- SoccerTwos/SoccerTwos-48499998.pt +3 -0
- SoccerTwos/SoccerTwos-48999968.onnx +3 -0
- SoccerTwos/SoccerTwos-48999968.pt +3 -0
- SoccerTwos/SoccerTwos-49499924.onnx +3 -0
- SoccerTwos/SoccerTwos-49499924.pt +3 -0
- SoccerTwos/SoccerTwos-49999946.onnx +3 -0
- SoccerTwos/SoccerTwos-49999946.pt +3 -0
- SoccerTwos/SoccerTwos-50000232.onnx +3 -0
- SoccerTwos/SoccerTwos-50000232.pt +3 -0
- SoccerTwos/checkpoint.pt +1 -1
- SoccerTwos/events.out.tfevents.1711023583.magixn.925.0 +3 -0
- config.json +1 -1
- configuration.yaml +1 -1
- run_logs/Player-0.log +14 -14
- run_logs/timers.json +182 -182
- run_logs/training_status.json +24 -24
SoccerTwos.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1768747
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea84d713dd9a5281cd930a0d557bbfb84f2fcca51513d3659754f2061fe201ba
|
3 |
size 1768747
|
SoccerTwos/SoccerTwos-48499998.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a632f9d437986f866df0e9c41de74c60b58cde35c2d38c9b56683389d5a91c56
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-48499998.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2744057ff1d8c91e10ada09da48730ce2ec563f211020d15090731133fb328d1
|
3 |
+
size 28430482
|
SoccerTwos/SoccerTwos-48999968.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c803315c2d900301adfa59c6eaaf5db739902c0ae8cd3ed079ae74de7dc81a2
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-48999968.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6d3c6b1bd144548e5e76620d8cdc583ebe726598302b036901b79c6f3ce0471
|
3 |
+
size 28430482
|
SoccerTwos/SoccerTwos-49499924.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ee95f2d18b6c8548904903ec5a2d9020ab8c0a976c81c8d393a9c07be39937e
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-49499924.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f1ebbf664de0a26e01bc351807d02a9c2e20856ebf10bfa8e6ae235da45f76b
|
3 |
+
size 28430482
|
SoccerTwos/SoccerTwos-49999946.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea84d713dd9a5281cd930a0d557bbfb84f2fcca51513d3659754f2061fe201ba
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-49999946.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51c6d956026c65edda48ea588ba26dcbd94045d5f715613e420b5468cf44e9a5
|
3 |
+
size 28430482
|
SoccerTwos/SoccerTwos-50000232.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea84d713dd9a5281cd930a0d557bbfb84f2fcca51513d3659754f2061fe201ba
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-50000232.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d88bbe9c30236802eea4de9d920539dc36eddff32cd40b33b639fe2b14fa8b85
|
3 |
+
size 28430482
|
SoccerTwos/checkpoint.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 28429366
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73da84a4f8eefc4c1e90361e8d017348638e724b91698e9938ddd316d87e6406
|
3 |
size 28429366
|
SoccerTwos/events.out.tfevents.1711023583.magixn.925.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:502b3d2536ca3bb25fbd6df9b2b1bd514ce1366ceba912f22ce4d1ef91d979c2
|
3 |
+
size 30835017
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "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": 5, "even_checkpoints": false, "max_steps":
|
|
|
1 |
+
{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "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": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "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": "SoccerTwos", "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
@@ -37,7 +37,7 @@ behaviors:
|
|
37 |
init_path: null
|
38 |
keep_checkpoints: 5
|
39 |
even_checkpoints: false
|
40 |
-
max_steps:
|
41 |
time_horizon: 1000
|
42 |
summary_freq: 10000
|
43 |
threaded: false
|
|
|
37 |
init_path: null
|
38 |
keep_checkpoints: 5
|
39 |
even_checkpoints: false
|
40 |
+
max_steps: 50000000
|
41 |
time_horizon: 1000
|
42 |
summary_freq: 10000
|
43 |
threaded: false
|
run_logs/Player-0.log
CHANGED
@@ -11,7 +11,7 @@ NullGfxDevice:
|
|
11 |
Renderer: Null Device
|
12 |
Vendor: Unity Technologies
|
13 |
Begin MonoManager ReloadAssembly
|
14 |
-
- Completed reload, in 0.
|
15 |
ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
16 |
ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
17 |
ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
@@ -36,7 +36,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
|
|
36 |
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
37 |
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
38 |
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
39 |
-
UnloadTime:
|
40 |
Registered Communicator in Agent.
|
41 |
ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
42 |
requesting resize 84 x 84
|
@@ -45,7 +45,7 @@ Memory Statistics:
|
|
45 |
[ALLOC_TEMP_TLS] TLS Allocator
|
46 |
StackAllocators :
|
47 |
[ALLOC_TEMP_MAIN]
|
48 |
-
Peak usage frame count: [8.0 KB-16.0 KB]:
|
49 |
Initial Block Size 4.0 MB
|
50 |
Current Block Size 4.0 MB
|
51 |
Peak Allocated Bytes 2.1 MB
|
@@ -191,22 +191,22 @@ Memory Statistics:
|
|
191 |
Peak Allocated Bytes 0 B
|
192 |
Overflow Count 0
|
193 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
194 |
-
Peak main deferred allocation count
|
195 |
[ALLOC_BUCKET]
|
196 |
Large Block size 4.0 MB
|
197 |
Used Block count 1
|
198 |
Peak Allocated bytes 1.0 MB
|
199 |
[ALLOC_DEFAULT_MAIN]
|
200 |
-
Peak usage frame count: [4.0 MB-8.0 MB]:
|
201 |
Requested Block Size 16.0 MB
|
202 |
Peak Block count 1
|
203 |
-
Peak Allocated memory 4.
|
204 |
Peak Large allocation bytes 0 B
|
205 |
[ALLOC_DEFAULT_THREAD]
|
206 |
-
Peak usage frame count: [16.0 MB-32.0 MB]:
|
207 |
Requested Block Size 16.0 MB
|
208 |
Peak Block count 1
|
209 |
-
Peak Allocated memory 17.
|
210 |
Peak Large allocation bytes 16.0 MB
|
211 |
[ALLOC_TEMP_JOB_1_FRAME]
|
212 |
Initial Block Size 2.0 MB
|
@@ -235,13 +235,13 @@ Memory Statistics:
|
|
235 |
Used Block count 1
|
236 |
Peak Allocated bytes 1.0 MB
|
237 |
[ALLOC_GFX_MAIN]
|
238 |
-
Peak usage frame count: [32.0 KB-64.0 KB]:
|
239 |
Requested Block Size 16.0 MB
|
240 |
Peak Block count 1
|
241 |
Peak Allocated memory 65.6 KB
|
242 |
Peak Large allocation bytes 0 B
|
243 |
[ALLOC_GFX_THREAD]
|
244 |
-
Peak usage frame count: [128.0 KB-256.0 KB]:
|
245 |
Requested Block Size 16.0 MB
|
246 |
Peak Block count 1
|
247 |
Peak Allocated memory 173.5 KB
|
@@ -253,13 +253,13 @@ Memory Statistics:
|
|
253 |
Used Block count 1
|
254 |
Peak Allocated bytes 1.0 MB
|
255 |
[ALLOC_CACHEOBJECTS_MAIN]
|
256 |
-
Peak usage frame count: [0.5 MB-1.0 MB]:
|
257 |
Requested Block Size 4.0 MB
|
258 |
Peak Block count 1
|
259 |
Peak Allocated memory 0.6 MB
|
260 |
Peak Large allocation bytes 0 B
|
261 |
[ALLOC_CACHEOBJECTS_THREAD]
|
262 |
-
Peak usage frame count: [0.5 MB-1.0 MB]:
|
263 |
Requested Block Size 4.0 MB
|
264 |
Peak Block count 2
|
265 |
Peak Allocated memory 4.5 MB
|
@@ -271,13 +271,13 @@ Memory Statistics:
|
|
271 |
Used Block count 1
|
272 |
Peak Allocated bytes 1.0 MB
|
273 |
[ALLOC_TYPETREE_MAIN]
|
274 |
-
Peak usage frame count: [0-1.0 KB]:
|
275 |
Requested Block Size 2.0 MB
|
276 |
Peak Block count 1
|
277 |
Peak Allocated memory 1.0 KB
|
278 |
Peak Large allocation bytes 0 B
|
279 |
[ALLOC_TYPETREE_THREAD]
|
280 |
-
Peak usage frame count: [1.0 KB-2.0 KB]:
|
281 |
Requested Block Size 2.0 MB
|
282 |
Peak Block count 1
|
283 |
Peak Allocated memory 2.2 KB
|
|
|
11 |
Renderer: Null Device
|
12 |
Vendor: Unity Technologies
|
13 |
Begin MonoManager ReloadAssembly
|
14 |
+
- Completed reload, in 0.119 seconds
|
15 |
ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
16 |
ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
17 |
ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
|
|
36 |
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
37 |
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
38 |
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
39 |
+
UnloadTime: 0.923190 ms
|
40 |
Registered Communicator in Agent.
|
41 |
ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
42 |
requesting resize 84 x 84
|
|
|
45 |
[ALLOC_TEMP_TLS] TLS Allocator
|
46 |
StackAllocators :
|
47 |
[ALLOC_TEMP_MAIN]
|
48 |
+
Peak usage frame count: [8.0 KB-16.0 KB]: 564796 frames, [2.0 MB-4.0 MB]: 1 frames
|
49 |
Initial Block Size 4.0 MB
|
50 |
Current Block Size 4.0 MB
|
51 |
Peak Allocated Bytes 2.1 MB
|
|
|
191 |
Peak Allocated Bytes 0 B
|
192 |
Overflow Count 0
|
193 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
194 |
+
Peak main deferred allocation count 4
|
195 |
[ALLOC_BUCKET]
|
196 |
Large Block size 4.0 MB
|
197 |
Used Block count 1
|
198 |
Peak Allocated bytes 1.0 MB
|
199 |
[ALLOC_DEFAULT_MAIN]
|
200 |
+
Peak usage frame count: [4.0 MB-8.0 MB]: 564797 frames
|
201 |
Requested Block Size 16.0 MB
|
202 |
Peak Block count 1
|
203 |
+
Peak Allocated memory 4.9 MB
|
204 |
Peak Large allocation bytes 0 B
|
205 |
[ALLOC_DEFAULT_THREAD]
|
206 |
+
Peak usage frame count: [16.0 MB-32.0 MB]: 564797 frames
|
207 |
Requested Block Size 16.0 MB
|
208 |
Peak Block count 1
|
209 |
+
Peak Allocated memory 17.3 MB
|
210 |
Peak Large allocation bytes 16.0 MB
|
211 |
[ALLOC_TEMP_JOB_1_FRAME]
|
212 |
Initial Block Size 2.0 MB
|
|
|
235 |
Used Block count 1
|
236 |
Peak Allocated bytes 1.0 MB
|
237 |
[ALLOC_GFX_MAIN]
|
238 |
+
Peak usage frame count: [32.0 KB-64.0 KB]: 564796 frames, [64.0 KB-128.0 KB]: 1 frames
|
239 |
Requested Block Size 16.0 MB
|
240 |
Peak Block count 1
|
241 |
Peak Allocated memory 65.6 KB
|
242 |
Peak Large allocation bytes 0 B
|
243 |
[ALLOC_GFX_THREAD]
|
244 |
+
Peak usage frame count: [128.0 KB-256.0 KB]: 564797 frames
|
245 |
Requested Block Size 16.0 MB
|
246 |
Peak Block count 1
|
247 |
Peak Allocated memory 173.5 KB
|
|
|
253 |
Used Block count 1
|
254 |
Peak Allocated bytes 1.0 MB
|
255 |
[ALLOC_CACHEOBJECTS_MAIN]
|
256 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 564797 frames
|
257 |
Requested Block Size 4.0 MB
|
258 |
Peak Block count 1
|
259 |
Peak Allocated memory 0.6 MB
|
260 |
Peak Large allocation bytes 0 B
|
261 |
[ALLOC_CACHEOBJECTS_THREAD]
|
262 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 564796 frames, [4.0 MB-8.0 MB]: 1 frames
|
263 |
Requested Block Size 4.0 MB
|
264 |
Peak Block count 2
|
265 |
Peak Allocated memory 4.5 MB
|
|
|
271 |
Used Block count 1
|
272 |
Peak Allocated bytes 1.0 MB
|
273 |
[ALLOC_TYPETREE_MAIN]
|
274 |
+
Peak usage frame count: [0-1.0 KB]: 564797 frames
|
275 |
Requested Block Size 2.0 MB
|
276 |
Peak Block count 1
|
277 |
Peak Allocated memory 1.0 KB
|
278 |
Peak Large allocation bytes 0 B
|
279 |
[ALLOC_TYPETREE_THREAD]
|
280 |
+
Peak usage frame count: [1.0 KB-2.0 KB]: 564796 frames, [2.0 KB-4.0 KB]: 1 frames
|
281 |
Requested Block Size 2.0 MB
|
282 |
Peak Block count 1
|
283 |
Peak Allocated memory 2.2 KB
|
run_logs/timers.json
CHANGED
@@ -2,201 +2,201 @@
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"SoccerTwos.Policy.Entropy.mean": {
|
5 |
-
"value": 1.
|
6 |
-
"min": 1.
|
7 |
-
"max": 1.
|
8 |
-
"count":
|
9 |
},
|
10 |
"SoccerTwos.Policy.Entropy.sum": {
|
11 |
-
"value":
|
12 |
-
"min":
|
13 |
-
"max":
|
14 |
-
"count":
|
15 |
},
|
16 |
"SoccerTwos.Environment.EpisodeLength.mean": {
|
17 |
-
"value":
|
18 |
-
"min":
|
19 |
-
"max":
|
20 |
-
"count":
|
21 |
},
|
22 |
"SoccerTwos.Environment.EpisodeLength.sum": {
|
23 |
-
"value":
|
24 |
-
"min":
|
25 |
-
"max":
|
26 |
-
"count":
|
27 |
},
|
28 |
"SoccerTwos.Self-play.ELO.mean": {
|
29 |
-
"value":
|
30 |
-
"min":
|
31 |
-
"max":
|
32 |
-
"count":
|
33 |
},
|
34 |
"SoccerTwos.Self-play.ELO.sum": {
|
35 |
-
"value":
|
36 |
-
"min":
|
37 |
-
"max":
|
38 |
-
"count":
|
39 |
},
|
40 |
"SoccerTwos.Step.mean": {
|
41 |
-
"value":
|
42 |
-
"min":
|
43 |
-
"max":
|
44 |
-
"count":
|
45 |
},
|
46 |
"SoccerTwos.Step.sum": {
|
47 |
-
"value":
|
48 |
-
"min":
|
49 |
-
"max":
|
50 |
-
"count":
|
51 |
},
|
52 |
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
53 |
-
"value": -0.
|
54 |
-
"min": -0.
|
55 |
-
"max": 0.
|
56 |
-
"count":
|
57 |
},
|
58 |
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
59 |
-
"value": -
|
60 |
-
"min": -
|
61 |
-
"max":
|
62 |
-
"count":
|
63 |
},
|
64 |
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
65 |
-
"value": -0.
|
66 |
-
"min": -0.
|
67 |
-
"max": 0.
|
68 |
-
"count":
|
69 |
},
|
70 |
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
71 |
-
"value": -
|
72 |
-
"min": -
|
73 |
-
"max":
|
74 |
-
"count":
|
75 |
},
|
76 |
"SoccerTwos.Environment.CumulativeReward.mean": {
|
77 |
"value": 0.0,
|
78 |
"min": 0.0,
|
79 |
"max": 0.0,
|
80 |
-
"count":
|
81 |
},
|
82 |
"SoccerTwos.Environment.CumulativeReward.sum": {
|
83 |
"value": 0.0,
|
84 |
"min": 0.0,
|
85 |
"max": 0.0,
|
86 |
-
"count":
|
87 |
},
|
88 |
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
89 |
-
"value": 0.
|
90 |
-
"min": -0.
|
91 |
-
"max": 0.
|
92 |
-
"count":
|
93 |
},
|
94 |
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
95 |
-
"value":
|
96 |
-
"min": -
|
97 |
-
"max":
|
98 |
-
"count":
|
99 |
},
|
100 |
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
101 |
-
"value": 0.
|
102 |
-
"min": -0.
|
103 |
-
"max": 0.
|
104 |
-
"count":
|
105 |
},
|
106 |
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
107 |
-
"value":
|
108 |
-
"min": -
|
109 |
-
"max":
|
110 |
-
"count":
|
111 |
},
|
112 |
"SoccerTwos.IsTraining.mean": {
|
113 |
"value": 1.0,
|
114 |
"min": 1.0,
|
115 |
"max": 1.0,
|
116 |
-
"count":
|
117 |
},
|
118 |
"SoccerTwos.IsTraining.sum": {
|
119 |
"value": 1.0,
|
120 |
"min": 1.0,
|
121 |
"max": 1.0,
|
122 |
-
"count":
|
123 |
},
|
124 |
"SoccerTwos.Losses.PolicyLoss.mean": {
|
125 |
-
"value": 0.
|
126 |
-
"min": 0.
|
127 |
-
"max": 0.
|
128 |
-
"count":
|
129 |
},
|
130 |
"SoccerTwos.Losses.PolicyLoss.sum": {
|
131 |
-
"value": 0.
|
132 |
-
"min": 0.
|
133 |
-
"max": 0.
|
134 |
-
"count":
|
135 |
},
|
136 |
"SoccerTwos.Losses.ValueLoss.mean": {
|
137 |
-
"value": 0.
|
138 |
-
"min": 0.
|
139 |
-
"max": 0.
|
140 |
-
"count":
|
141 |
},
|
142 |
"SoccerTwos.Losses.ValueLoss.sum": {
|
143 |
-
"value": 0.
|
144 |
-
"min": 0.
|
145 |
-
"max": 0.
|
146 |
-
"count":
|
147 |
},
|
148 |
"SoccerTwos.Losses.BaselineLoss.mean": {
|
149 |
-
"value": 0.
|
150 |
-
"min": 0.
|
151 |
-
"max": 0.
|
152 |
-
"count":
|
153 |
},
|
154 |
"SoccerTwos.Losses.BaselineLoss.sum": {
|
155 |
-
"value": 0.
|
156 |
-
"min": 0.
|
157 |
-
"max": 0.
|
158 |
-
"count":
|
159 |
},
|
160 |
"SoccerTwos.Policy.LearningRate.mean": {
|
161 |
"value": 0.0003,
|
162 |
"min": 0.0003,
|
163 |
"max": 0.0003,
|
164 |
-
"count":
|
165 |
},
|
166 |
"SoccerTwos.Policy.LearningRate.sum": {
|
167 |
"value": 0.0003,
|
168 |
"min": 0.0003,
|
169 |
"max": 0.0003,
|
170 |
-
"count":
|
171 |
},
|
172 |
"SoccerTwos.Policy.Epsilon.mean": {
|
173 |
"value": 0.20000000000000007,
|
174 |
"min": 0.20000000000000007,
|
175 |
"max": 0.20000000000000007,
|
176 |
-
"count":
|
177 |
},
|
178 |
"SoccerTwos.Policy.Epsilon.sum": {
|
179 |
"value": 0.20000000000000007,
|
180 |
"min": 0.20000000000000007,
|
181 |
"max": 0.20000000000000007,
|
182 |
-
"count":
|
183 |
},
|
184 |
"SoccerTwos.Policy.Beta.mean": {
|
185 |
"value": 0.005000000000000001,
|
186 |
"min": 0.005000000000000001,
|
187 |
"max": 0.005000000000000001,
|
188 |
-
"count":
|
189 |
},
|
190 |
"SoccerTwos.Policy.Beta.sum": {
|
191 |
"value": 0.005000000000000001,
|
192 |
"min": 0.005000000000000001,
|
193 |
"max": 0.005000000000000001,
|
194 |
-
"count":
|
195 |
}
|
196 |
},
|
197 |
"metadata": {
|
198 |
"timer_format_version": "0.1.0",
|
199 |
-
"start_time_seconds": "
|
200 |
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
|
201 |
"command_line_arguments": "/home/magixn/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
|
202 |
"mlagents_version": "1.1.0.dev0",
|
@@ -204,59 +204,59 @@
|
|
204 |
"communication_protocol_version": "1.5.0",
|
205 |
"pytorch_version": "2.2.1+cu121",
|
206 |
"numpy_version": "1.23.5",
|
207 |
-
"end_time_seconds": "
|
208 |
},
|
209 |
-
"total":
|
210 |
"count": 1,
|
211 |
-
"self": 10.
|
212 |
"children": {
|
213 |
"run_training.setup": {
|
214 |
-
"total": 0.
|
215 |
"count": 1,
|
216 |
-
"self": 0.
|
217 |
},
|
218 |
"TrainerController.start_learning": {
|
219 |
-
"total":
|
220 |
"count": 1,
|
221 |
-
"self":
|
222 |
"children": {
|
223 |
"TrainerController._reset_env": {
|
224 |
-
"total":
|
225 |
-
"count":
|
226 |
-
"self":
|
227 |
},
|
228 |
"TrainerController.advance": {
|
229 |
-
"total":
|
230 |
-
"count":
|
231 |
-
"self":
|
232 |
"children": {
|
233 |
"env_step": {
|
234 |
-
"total":
|
235 |
-
"count":
|
236 |
-
"self":
|
237 |
"children": {
|
238 |
"SubprocessEnvManager._take_step": {
|
239 |
-
"total":
|
240 |
-
"count":
|
241 |
-
"self":
|
242 |
"children": {
|
243 |
"TorchPolicy.evaluate": {
|
244 |
-
"total":
|
245 |
-
"count":
|
246 |
-
"self":
|
247 |
}
|
248 |
}
|
249 |
},
|
250 |
"workers": {
|
251 |
-
"total":
|
252 |
-
"count":
|
253 |
"self": 0.0,
|
254 |
"children": {
|
255 |
"worker_root": {
|
256 |
-
"total":
|
257 |
-
"count":
|
258 |
"is_parallel": true,
|
259 |
-
"self":
|
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.
|
269 |
"count": 2,
|
270 |
"is_parallel": true,
|
271 |
-
"self": 0.
|
272 |
"children": {
|
273 |
"_process_rank_one_or_two_observation": {
|
274 |
-
"total": 0.
|
275 |
"count": 8,
|
276 |
"is_parallel": true,
|
277 |
-
"self": 0.
|
278 |
}
|
279 |
}
|
280 |
},
|
281 |
"UnityEnvironment.step": {
|
282 |
-
"total": 0.
|
283 |
"count": 1,
|
284 |
"is_parallel": true,
|
285 |
-
"self": 0.
|
286 |
"children": {
|
287 |
"UnityEnvironment._generate_step_input": {
|
288 |
-
"total": 0.
|
289 |
"count": 1,
|
290 |
"is_parallel": true,
|
291 |
-
"self": 0.
|
292 |
},
|
293 |
"communicator.exchange": {
|
294 |
-
"total": 0.
|
295 |
"count": 1,
|
296 |
"is_parallel": true,
|
297 |
-
"self": 0.
|
298 |
},
|
299 |
"steps_from_proto": {
|
300 |
-
"total": 0.
|
301 |
"count": 2,
|
302 |
"is_parallel": true,
|
303 |
-
"self": 0.
|
304 |
"children": {
|
305 |
"_process_rank_one_or_two_observation": {
|
306 |
-
"total": 0.
|
307 |
"count": 8,
|
308 |
"is_parallel": true,
|
309 |
-
"self": 0.
|
310 |
}
|
311 |
}
|
312 |
}
|
@@ -315,48 +315,48 @@
|
|
315 |
}
|
316 |
},
|
317 |
"steps_from_proto": {
|
318 |
-
"total": 0.
|
319 |
-
"count":
|
320 |
"is_parallel": true,
|
321 |
-
"self": 0.
|
322 |
"children": {
|
323 |
"_process_rank_one_or_two_observation": {
|
324 |
-
"total": 0.
|
325 |
-
"count":
|
326 |
"is_parallel": true,
|
327 |
-
"self": 0.
|
328 |
}
|
329 |
}
|
330 |
},
|
331 |
"UnityEnvironment.step": {
|
332 |
-
"total":
|
333 |
-
"count":
|
334 |
"is_parallel": true,
|
335 |
-
"self":
|
336 |
"children": {
|
337 |
"UnityEnvironment._generate_step_input": {
|
338 |
-
"total":
|
339 |
-
"count":
|
340 |
"is_parallel": true,
|
341 |
-
"self":
|
342 |
},
|
343 |
"communicator.exchange": {
|
344 |
-
"total":
|
345 |
-
"count":
|
346 |
"is_parallel": true,
|
347 |
-
"self":
|
348 |
},
|
349 |
"steps_from_proto": {
|
350 |
-
"total":
|
351 |
-
"count":
|
352 |
"is_parallel": true,
|
353 |
-
"self":
|
354 |
"children": {
|
355 |
"_process_rank_one_or_two_observation": {
|
356 |
-
"total":
|
357 |
-
"count":
|
358 |
"is_parallel": true,
|
359 |
-
"self":
|
360 |
}
|
361 |
}
|
362 |
}
|
@@ -369,31 +369,31 @@
|
|
369 |
}
|
370 |
},
|
371 |
"trainer_advance": {
|
372 |
-
"total":
|
373 |
-
"count":
|
374 |
-
"self":
|
375 |
"children": {
|
376 |
"process_trajectory": {
|
377 |
-
"total":
|
378 |
-
"count":
|
379 |
-
"self":
|
380 |
"children": {
|
381 |
"RLTrainer._checkpoint": {
|
382 |
-
"total":
|
383 |
-
"count":
|
384 |
-
"self":
|
385 |
}
|
386 |
}
|
387 |
},
|
388 |
"_update_policy": {
|
389 |
-
"total":
|
390 |
-
"count":
|
391 |
-
"self":
|
392 |
"children": {
|
393 |
"TorchPOCAOptimizer.update": {
|
394 |
-
"total":
|
395 |
-
"count":
|
396 |
-
"self":
|
397 |
}
|
398 |
}
|
399 |
}
|
@@ -402,19 +402,19 @@
|
|
402 |
}
|
403 |
},
|
404 |
"trainer_threads": {
|
405 |
-
"total":
|
406 |
"count": 1,
|
407 |
-
"self":
|
408 |
},
|
409 |
"TrainerController._save_models": {
|
410 |
-
"total": 0.
|
411 |
"count": 1,
|
412 |
-
"self": 0.
|
413 |
"children": {
|
414 |
"RLTrainer._checkpoint": {
|
415 |
-
"total": 0.
|
416 |
"count": 1,
|
417 |
-
"self": 0.
|
418 |
}
|
419 |
}
|
420 |
}
|
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"SoccerTwos.Policy.Entropy.mean": {
|
5 |
+
"value": 1.4757105112075806,
|
6 |
+
"min": 1.215389370918274,
|
7 |
+
"max": 1.5331782102584839,
|
8 |
+
"count": 3000
|
9 |
},
|
10 |
"SoccerTwos.Policy.Entropy.sum": {
|
11 |
+
"value": 30458.6640625,
|
12 |
+
"min": 22295.75390625,
|
13 |
+
"max": 35608.2890625,
|
14 |
+
"count": 3000
|
15 |
},
|
16 |
"SoccerTwos.Environment.EpisodeLength.mean": {
|
17 |
+
"value": 63.25974025974026,
|
18 |
+
"min": 36.84090909090909,
|
19 |
+
"max": 103.41666666666667,
|
20 |
+
"count": 3000
|
21 |
},
|
22 |
"SoccerTwos.Environment.EpisodeLength.sum": {
|
23 |
+
"value": 19484.0,
|
24 |
+
"min": 18048.0,
|
25 |
+
"max": 21840.0,
|
26 |
+
"count": 3000
|
27 |
},
|
28 |
"SoccerTwos.Self-play.ELO.mean": {
|
29 |
+
"value": 1573.6766903110993,
|
30 |
+
"min": 1442.8773657611414,
|
31 |
+
"max": 1663.9050228287604,
|
32 |
+
"count": 3000
|
33 |
},
|
34 |
"SoccerTwos.Self-play.ELO.sum": {
|
35 |
+
"value": 242346.2103079093,
|
36 |
+
"min": 154046.1627968983,
|
37 |
+
"max": 402418.1796228269,
|
38 |
+
"count": 3000
|
39 |
},
|
40 |
"SoccerTwos.Step.mean": {
|
41 |
+
"value": 49999946.0,
|
42 |
+
"min": 20009996.0,
|
43 |
+
"max": 49999946.0,
|
44 |
+
"count": 3000
|
45 |
},
|
46 |
"SoccerTwos.Step.sum": {
|
47 |
+
"value": 49999946.0,
|
48 |
+
"min": 20009996.0,
|
49 |
+
"max": 49999946.0,
|
50 |
+
"count": 3000
|
51 |
},
|
52 |
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
53 |
+
"value": -0.027925865724682808,
|
54 |
+
"min": -0.13085119426250458,
|
55 |
+
"max": 0.09527774900197983,
|
56 |
+
"count": 3000
|
57 |
},
|
58 |
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
59 |
+
"value": -4.328509330749512,
|
60 |
+
"min": -28.29364776611328,
|
61 |
+
"max": 18.740930557250977,
|
62 |
+
"count": 3000
|
63 |
},
|
64 |
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
65 |
+
"value": -0.027023281902074814,
|
66 |
+
"min": -0.1322842240333557,
|
67 |
+
"max": 0.09797108918428421,
|
68 |
+
"count": 3000
|
69 |
},
|
70 |
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
71 |
+
"value": -4.188608646392822,
|
72 |
+
"min": -28.20203399658203,
|
73 |
+
"max": 19.740550994873047,
|
74 |
+
"count": 3000
|
75 |
},
|
76 |
"SoccerTwos.Environment.CumulativeReward.mean": {
|
77 |
"value": 0.0,
|
78 |
"min": 0.0,
|
79 |
"max": 0.0,
|
80 |
+
"count": 3000
|
81 |
},
|
82 |
"SoccerTwos.Environment.CumulativeReward.sum": {
|
83 |
"value": 0.0,
|
84 |
"min": 0.0,
|
85 |
"max": 0.0,
|
86 |
+
"count": 3000
|
87 |
},
|
88 |
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
89 |
+
"value": 0.08620903222791611,
|
90 |
+
"min": -0.4535480030377706,
|
91 |
+
"max": 0.3041645398376681,
|
92 |
+
"count": 3000
|
93 |
},
|
94 |
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
95 |
+
"value": 13.362399995326996,
|
96 |
+
"min": -68.32039994001389,
|
97 |
+
"max": 55.68720030784607,
|
98 |
+
"count": 3000
|
99 |
},
|
100 |
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
101 |
+
"value": 0.08620903222791611,
|
102 |
+
"min": -0.4535480030377706,
|
103 |
+
"max": 0.3041645398376681,
|
104 |
+
"count": 3000
|
105 |
},
|
106 |
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
107 |
+
"value": 13.362399995326996,
|
108 |
+
"min": -68.32039994001389,
|
109 |
+
"max": 55.68720030784607,
|
110 |
+
"count": 3000
|
111 |
},
|
112 |
"SoccerTwos.IsTraining.mean": {
|
113 |
"value": 1.0,
|
114 |
"min": 1.0,
|
115 |
"max": 1.0,
|
116 |
+
"count": 3000
|
117 |
},
|
118 |
"SoccerTwos.IsTraining.sum": {
|
119 |
"value": 1.0,
|
120 |
"min": 1.0,
|
121 |
"max": 1.0,
|
122 |
+
"count": 3000
|
123 |
},
|
124 |
"SoccerTwos.Losses.PolicyLoss.mean": {
|
125 |
+
"value": 0.01824698790248173,
|
126 |
+
"min": 0.010630287903283412,
|
127 |
+
"max": 0.02478914411816125,
|
128 |
+
"count": 1456
|
129 |
},
|
130 |
"SoccerTwos.Losses.PolicyLoss.sum": {
|
131 |
+
"value": 0.01824698790248173,
|
132 |
+
"min": 0.010630287903283412,
|
133 |
+
"max": 0.02478914411816125,
|
134 |
+
"count": 1456
|
135 |
},
|
136 |
"SoccerTwos.Losses.ValueLoss.mean": {
|
137 |
+
"value": 0.08349171156684558,
|
138 |
+
"min": 0.07642882963021597,
|
139 |
+
"max": 0.13404745186368625,
|
140 |
+
"count": 1456
|
141 |
},
|
142 |
"SoccerTwos.Losses.ValueLoss.sum": {
|
143 |
+
"value": 0.08349171156684558,
|
144 |
+
"min": 0.07642882963021597,
|
145 |
+
"max": 0.13404745186368625,
|
146 |
+
"count": 1456
|
147 |
},
|
148 |
"SoccerTwos.Losses.BaselineLoss.mean": {
|
149 |
+
"value": 0.08438854391376177,
|
150 |
+
"min": 0.0767000397046407,
|
151 |
+
"max": 0.13709546675284703,
|
152 |
+
"count": 1456
|
153 |
},
|
154 |
"SoccerTwos.Losses.BaselineLoss.sum": {
|
155 |
+
"value": 0.08438854391376177,
|
156 |
+
"min": 0.0767000397046407,
|
157 |
+
"max": 0.13709546675284703,
|
158 |
+
"count": 1456
|
159 |
},
|
160 |
"SoccerTwos.Policy.LearningRate.mean": {
|
161 |
"value": 0.0003,
|
162 |
"min": 0.0003,
|
163 |
"max": 0.0003,
|
164 |
+
"count": 1456
|
165 |
},
|
166 |
"SoccerTwos.Policy.LearningRate.sum": {
|
167 |
"value": 0.0003,
|
168 |
"min": 0.0003,
|
169 |
"max": 0.0003,
|
170 |
+
"count": 1456
|
171 |
},
|
172 |
"SoccerTwos.Policy.Epsilon.mean": {
|
173 |
"value": 0.20000000000000007,
|
174 |
"min": 0.20000000000000007,
|
175 |
"max": 0.20000000000000007,
|
176 |
+
"count": 1456
|
177 |
},
|
178 |
"SoccerTwos.Policy.Epsilon.sum": {
|
179 |
"value": 0.20000000000000007,
|
180 |
"min": 0.20000000000000007,
|
181 |
"max": 0.20000000000000007,
|
182 |
+
"count": 1456
|
183 |
},
|
184 |
"SoccerTwos.Policy.Beta.mean": {
|
185 |
"value": 0.005000000000000001,
|
186 |
"min": 0.005000000000000001,
|
187 |
"max": 0.005000000000000001,
|
188 |
+
"count": 1456
|
189 |
},
|
190 |
"SoccerTwos.Policy.Beta.sum": {
|
191 |
"value": 0.005000000000000001,
|
192 |
"min": 0.005000000000000001,
|
193 |
"max": 0.005000000000000001,
|
194 |
+
"count": 1456
|
195 |
}
|
196 |
},
|
197 |
"metadata": {
|
198 |
"timer_format_version": "0.1.0",
|
199 |
+
"start_time_seconds": "1711023582",
|
200 |
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
|
201 |
"command_line_arguments": "/home/magixn/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
|
202 |
"mlagents_version": "1.1.0.dev0",
|
|
|
204 |
"communication_protocol_version": "1.5.0",
|
205 |
"pytorch_version": "2.2.1+cu121",
|
206 |
"numpy_version": "1.23.5",
|
207 |
+
"end_time_seconds": "1711133055"
|
208 |
},
|
209 |
+
"total": 109472.44741512701,
|
210 |
"count": 1,
|
211 |
+
"self": 10.013290245013195,
|
212 |
"children": {
|
213 |
"run_training.setup": {
|
214 |
+
"total": 0.03806096100001355,
|
215 |
"count": 1,
|
216 |
+
"self": 0.03806096100001355
|
217 |
},
|
218 |
"TrainerController.start_learning": {
|
219 |
+
"total": 109462.396063921,
|
220 |
"count": 1,
|
221 |
+
"self": 73.4563194719085,
|
222 |
"children": {
|
223 |
"TrainerController._reset_env": {
|
224 |
+
"total": 7.119639347978875,
|
225 |
+
"count": 151,
|
226 |
+
"self": 7.119639347978875
|
227 |
},
|
228 |
"TrainerController.advance": {
|
229 |
+
"total": 109381.6259710041,
|
230 |
+
"count": 2082683,
|
231 |
+
"self": 80.5391434408084,
|
232 |
"children": {
|
233 |
"env_step": {
|
234 |
+
"total": 53412.314257703205,
|
235 |
+
"count": 2082683,
|
236 |
+
"self": 43623.686861552116,
|
237 |
"children": {
|
238 |
"SubprocessEnvManager._take_step": {
|
239 |
+
"total": 9743.353611256794,
|
240 |
+
"count": 2082683,
|
241 |
+
"self": 376.12653230122123,
|
242 |
"children": {
|
243 |
"TorchPolicy.evaluate": {
|
244 |
+
"total": 9367.227078955573,
|
245 |
+
"count": 3765364,
|
246 |
+
"self": 9367.227078955573
|
247 |
}
|
248 |
}
|
249 |
},
|
250 |
"workers": {
|
251 |
+
"total": 45.2737848942956,
|
252 |
+
"count": 2082683,
|
253 |
"self": 0.0,
|
254 |
"children": {
|
255 |
"worker_root": {
|
256 |
+
"total": 109318.56385391075,
|
257 |
+
"count": 2082683,
|
258 |
"is_parallel": true,
|
259 |
+
"self": 73007.71565440437,
|
260 |
"children": {
|
261 |
"run_training.setup": {
|
262 |
"total": 0.0,
|
|
|
265 |
"self": 0.0,
|
266 |
"children": {
|
267 |
"steps_from_proto": {
|
268 |
+
"total": 0.004155171999968843,
|
269 |
"count": 2,
|
270 |
"is_parallel": true,
|
271 |
+
"self": 0.0018411529999582399,
|
272 |
"children": {
|
273 |
"_process_rank_one_or_two_observation": {
|
274 |
+
"total": 0.002314019000010603,
|
275 |
"count": 8,
|
276 |
"is_parallel": true,
|
277 |
+
"self": 0.002314019000010603
|
278 |
}
|
279 |
}
|
280 |
},
|
281 |
"UnityEnvironment.step": {
|
282 |
+
"total": 0.04638103199999932,
|
283 |
"count": 1,
|
284 |
"is_parallel": true,
|
285 |
+
"self": 0.0008324190000053022,
|
286 |
"children": {
|
287 |
"UnityEnvironment._generate_step_input": {
|
288 |
+
"total": 0.000863132000006317,
|
289 |
"count": 1,
|
290 |
"is_parallel": true,
|
291 |
+
"self": 0.000863132000006317
|
292 |
},
|
293 |
"communicator.exchange": {
|
294 |
+
"total": 0.04250551100000166,
|
295 |
"count": 1,
|
296 |
"is_parallel": true,
|
297 |
+
"self": 0.04250551100000166
|
298 |
},
|
299 |
"steps_from_proto": {
|
300 |
+
"total": 0.0021799699999860422,
|
301 |
"count": 2,
|
302 |
"is_parallel": true,
|
303 |
+
"self": 0.0005233989999737787,
|
304 |
"children": {
|
305 |
"_process_rank_one_or_two_observation": {
|
306 |
+
"total": 0.0016565710000122635,
|
307 |
"count": 8,
|
308 |
"is_parallel": true,
|
309 |
+
"self": 0.0016565710000122635
|
310 |
}
|
311 |
}
|
312 |
}
|
|
|
315 |
}
|
316 |
},
|
317 |
"steps_from_proto": {
|
318 |
+
"total": 0.3322439869853895,
|
319 |
+
"count": 300,
|
320 |
"is_parallel": true,
|
321 |
+
"self": 0.07504584902235933,
|
322 |
"children": {
|
323 |
"_process_rank_one_or_two_observation": {
|
324 |
+
"total": 0.25719813796303015,
|
325 |
+
"count": 1200,
|
326 |
"is_parallel": true,
|
327 |
+
"self": 0.25719813796303015
|
328 |
}
|
329 |
}
|
330 |
},
|
331 |
"UnityEnvironment.step": {
|
332 |
+
"total": 36310.51595551938,
|
333 |
+
"count": 2082682,
|
334 |
"is_parallel": true,
|
335 |
+
"self": 1637.2535055873159,
|
336 |
"children": {
|
337 |
"UnityEnvironment._generate_step_input": {
|
338 |
+
"total": 1251.8232436233416,
|
339 |
+
"count": 2082682,
|
340 |
"is_parallel": true,
|
341 |
+
"self": 1251.8232436233416
|
342 |
},
|
343 |
"communicator.exchange": {
|
344 |
+
"total": 29081.51631062065,
|
345 |
+
"count": 2082682,
|
346 |
"is_parallel": true,
|
347 |
+
"self": 29081.51631062065
|
348 |
},
|
349 |
"steps_from_proto": {
|
350 |
+
"total": 4339.9228956880725,
|
351 |
+
"count": 4165364,
|
352 |
"is_parallel": true,
|
353 |
+
"self": 926.6103741319807,
|
354 |
"children": {
|
355 |
"_process_rank_one_or_two_observation": {
|
356 |
+
"total": 3413.3125215560917,
|
357 |
+
"count": 16661456,
|
358 |
"is_parallel": true,
|
359 |
+
"self": 3413.3125215560917
|
360 |
}
|
361 |
}
|
362 |
}
|
|
|
369 |
}
|
370 |
},
|
371 |
"trainer_advance": {
|
372 |
+
"total": 55888.772569860084,
|
373 |
+
"count": 2082683,
|
374 |
+
"self": 638.9373073734241,
|
375 |
"children": {
|
376 |
"process_trajectory": {
|
377 |
+
"total": 10660.703185951563,
|
378 |
+
"count": 2082683,
|
379 |
+
"self": 10646.131815530573,
|
380 |
"children": {
|
381 |
"RLTrainer._checkpoint": {
|
382 |
+
"total": 14.571370420989979,
|
383 |
+
"count": 60,
|
384 |
+
"self": 14.571370420989979
|
385 |
}
|
386 |
}
|
387 |
},
|
388 |
"_update_policy": {
|
389 |
+
"total": 44589.1320765351,
|
390 |
+
"count": 1456,
|
391 |
+
"self": 6212.25272581703,
|
392 |
"children": {
|
393 |
"TorchPOCAOptimizer.update": {
|
394 |
+
"total": 38376.87935071807,
|
395 |
+
"count": 43680,
|
396 |
+
"self": 38376.87935071807
|
397 |
}
|
398 |
}
|
399 |
}
|
|
|
402 |
}
|
403 |
},
|
404 |
"trainer_threads": {
|
405 |
+
"total": 2.2040039766579866e-06,
|
406 |
"count": 1,
|
407 |
+
"self": 2.2040039766579866e-06
|
408 |
},
|
409 |
"TrainerController._save_models": {
|
410 |
+
"total": 0.1941318930039415,
|
411 |
"count": 1,
|
412 |
+
"self": 0.0017999340052483603,
|
413 |
"children": {
|
414 |
"RLTrainer._checkpoint": {
|
415 |
+
"total": 0.19233195899869315,
|
416 |
"count": 1,
|
417 |
+
"self": 0.19233195899869315
|
418 |
}
|
419 |
}
|
420 |
}
|
run_logs/training_status.json
CHANGED
@@ -2,59 +2,59 @@
|
|
2 |
"SoccerTwos": {
|
3 |
"checkpoints": [
|
4 |
{
|
5 |
-
"steps":
|
6 |
-
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-
|
7 |
"reward": 0.0,
|
8 |
-
"creation_time":
|
9 |
"auxillary_file_paths": [
|
10 |
-
"results/SoccerTwos/SoccerTwos/SoccerTwos-
|
11 |
]
|
12 |
},
|
13 |
{
|
14 |
-
"steps":
|
15 |
-
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-
|
16 |
"reward": 0.0,
|
17 |
-
"creation_time":
|
18 |
"auxillary_file_paths": [
|
19 |
-
"results/SoccerTwos/SoccerTwos/SoccerTwos-
|
20 |
]
|
21 |
},
|
22 |
{
|
23 |
-
"steps":
|
24 |
-
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-
|
25 |
"reward": 0.0,
|
26 |
-
"creation_time":
|
27 |
"auxillary_file_paths": [
|
28 |
-
"results/SoccerTwos/SoccerTwos/SoccerTwos-
|
29 |
]
|
30 |
},
|
31 |
{
|
32 |
-
"steps":
|
33 |
-
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-
|
34 |
"reward": 0.0,
|
35 |
-
"creation_time":
|
36 |
"auxillary_file_paths": [
|
37 |
-
"results/SoccerTwos/SoccerTwos/SoccerTwos-
|
38 |
]
|
39 |
},
|
40 |
{
|
41 |
-
"steps":
|
42 |
-
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-
|
43 |
"reward": 0.0,
|
44 |
-
"creation_time":
|
45 |
"auxillary_file_paths": [
|
46 |
-
"results/SoccerTwos/SoccerTwos/SoccerTwos-
|
47 |
]
|
48 |
}
|
49 |
],
|
50 |
-
"elo":
|
51 |
"final_checkpoint": {
|
52 |
-
"steps":
|
53 |
"file_path": "results/SoccerTwos/SoccerTwos.onnx",
|
54 |
"reward": 0.0,
|
55 |
-
"creation_time":
|
56 |
"auxillary_file_paths": [
|
57 |
-
"results/SoccerTwos/SoccerTwos/SoccerTwos-
|
58 |
]
|
59 |
}
|
60 |
},
|
|
|
2 |
"SoccerTwos": {
|
3 |
"checkpoints": [
|
4 |
{
|
5 |
+
"steps": 48499998,
|
6 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499998.onnx",
|
7 |
"reward": 0.0,
|
8 |
+
"creation_time": 1711127187.6734087,
|
9 |
"auxillary_file_paths": [
|
10 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-48499998.pt"
|
11 |
]
|
12 |
},
|
13 |
{
|
14 |
+
"steps": 48999968,
|
15 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999968.onnx",
|
16 |
"reward": 0.0,
|
17 |
+
"creation_time": 1711129147.367645,
|
18 |
"auxillary_file_paths": [
|
19 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-48999968.pt"
|
20 |
]
|
21 |
},
|
22 |
{
|
23 |
+
"steps": 49499924,
|
24 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499924.onnx",
|
25 |
"reward": 0.0,
|
26 |
+
"creation_time": 1711131090.5125165,
|
27 |
"auxillary_file_paths": [
|
28 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-49499924.pt"
|
29 |
]
|
30 |
},
|
31 |
{
|
32 |
+
"steps": 49999946,
|
33 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999946.onnx",
|
34 |
"reward": 0.0,
|
35 |
+
"creation_time": 1711133044.7667835,
|
36 |
"auxillary_file_paths": [
|
37 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-49999946.pt"
|
38 |
]
|
39 |
},
|
40 |
{
|
41 |
+
"steps": 50000232,
|
42 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000232.onnx",
|
43 |
"reward": 0.0,
|
44 |
+
"creation_time": 1711133045.0290792,
|
45 |
"auxillary_file_paths": [
|
46 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-50000232.pt"
|
47 |
]
|
48 |
}
|
49 |
],
|
50 |
+
"elo": 1576.864615609649,
|
51 |
"final_checkpoint": {
|
52 |
+
"steps": 50000232,
|
53 |
"file_path": "results/SoccerTwos/SoccerTwos.onnx",
|
54 |
"reward": 0.0,
|
55 |
+
"creation_time": 1711133045.0290792,
|
56 |
"auxillary_file_paths": [
|
57 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-50000232.pt"
|
58 |
]
|
59 |
}
|
60 |
},
|