First push
Browse files- README.md +4 -4
- SoccerTwos.onnx +3 -0
- SoccerTwos/SoccerTwos-10226.onnx +3 -0
- SoccerTwos/SoccerTwos-10226.pt +3 -0
- SoccerTwos/checkpoint.pt +3 -0
- SoccerTwos/events.out.tfevents.1703231756.wkm0572l.11238.0 +3 -0
- config.json +1 -1
- configuration.yaml +4 -53
- run_logs/timers.json +185 -477
- run_logs/training_status.json +12 -89
README.md
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
---
|
2 |
library_name: ml-agents
|
3 |
tags:
|
4 |
-
-
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
-
- ML-Agents-
|
8 |
---
|
9 |
|
10 |
-
# **poca** Agent playing **
|
11 |
-
This is a trained model of a **poca** agent playing **
|
12 |
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
|
13 |
|
14 |
## Usage (with ML-Agents)
|
|
|
1 |
---
|
2 |
library_name: ml-agents
|
3 |
tags:
|
4 |
+
- SoccerTwos
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
+
- ML-Agents-SoccerTwos
|
8 |
---
|
9 |
|
10 |
+
# **poca** Agent playing **SoccerTwos**
|
11 |
+
This is a trained model of a **poca** agent playing **SoccerTwos**
|
12 |
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
|
13 |
|
14 |
## Usage (with ML-Agents)
|
SoccerTwos.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:275a0485aca002cd3c8515f9b79701644da1dbe14f450c70b6957227bbb42bc7
|
3 |
+
size 1766874
|
SoccerTwos/SoccerTwos-10226.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:275a0485aca002cd3c8515f9b79701644da1dbe14f450c70b6957227bbb42bc7
|
3 |
+
size 1766874
|
SoccerTwos/SoccerTwos-10226.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:009fbab2d9a53a6ef264f5e2d17c20c0b3acf7cdee5325cfc1fbba3ebab35e4f
|
3 |
+
size 9479442
|
SoccerTwos/checkpoint.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a06df9de48ce32dab3fb02eca880b901924b24aa7e3d2521f391886040579c0
|
3 |
+
size 9479202
|
SoccerTwos/events.out.tfevents.1703231756.wkm0572l.11238.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d85cfd3b8131f4551f237a5491837ff6a05060c2438e5f77a25d88095bb1e24
|
3 |
+
size 11296
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"default_settings": null, "behaviors": {"
|
|
|
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": 10000, "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": null, "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": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Soccer", "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
@@ -1,6 +1,6 @@
|
|
1 |
default_settings: null
|
2 |
behaviors:
|
3 |
-
|
4 |
trainer_type: poca
|
5 |
hyperparameters:
|
6 |
batch_size: 2048
|
@@ -37,63 +37,14 @@ 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
|
44 |
self_play:
|
45 |
save_steps: 50000
|
46 |
team_change: 200000
|
47 |
-
swap_steps:
|
48 |
-
window: 10
|
49 |
-
play_against_latest_model_ratio: 0.5
|
50 |
-
initial_elo: 1200.0
|
51 |
-
behavioral_cloning: null
|
52 |
-
Striker:
|
53 |
-
trainer_type: poca
|
54 |
-
hyperparameters:
|
55 |
-
batch_size: 2048
|
56 |
-
buffer_size: 20480
|
57 |
-
learning_rate: 0.0003
|
58 |
-
beta: 0.005
|
59 |
-
epsilon: 0.2
|
60 |
-
lambd: 0.95
|
61 |
-
num_epoch: 3
|
62 |
-
learning_rate_schedule: constant
|
63 |
-
beta_schedule: constant
|
64 |
-
epsilon_schedule: constant
|
65 |
-
checkpoint_interval: 500000
|
66 |
-
network_settings:
|
67 |
-
normalize: false
|
68 |
-
hidden_units: 512
|
69 |
-
num_layers: 2
|
70 |
-
vis_encode_type: simple
|
71 |
-
memory: null
|
72 |
-
goal_conditioning_type: hyper
|
73 |
-
deterministic: false
|
74 |
-
reward_signals:
|
75 |
-
extrinsic:
|
76 |
-
gamma: 0.99
|
77 |
-
strength: 1.0
|
78 |
-
network_settings:
|
79 |
-
normalize: false
|
80 |
-
hidden_units: 128
|
81 |
-
num_layers: 2
|
82 |
-
vis_encode_type: simple
|
83 |
-
memory: null
|
84 |
-
goal_conditioning_type: hyper
|
85 |
-
deterministic: false
|
86 |
-
init_path: null
|
87 |
-
keep_checkpoints: 5
|
88 |
-
even_checkpoints: false
|
89 |
-
max_steps: 30000000
|
90 |
-
time_horizon: 1000
|
91 |
-
summary_freq: 10000
|
92 |
-
threaded: false
|
93 |
-
self_play:
|
94 |
-
save_steps: 50000
|
95 |
-
team_change: 200000
|
96 |
-
swap_steps: 4000
|
97 |
window: 10
|
98 |
play_against_latest_model_ratio: 0.5
|
99 |
initial_elo: 1200.0
|
@@ -119,7 +70,7 @@ engine_settings:
|
|
119 |
no_graphics: false
|
120 |
environment_parameters: null
|
121 |
checkpoint_settings:
|
122 |
-
run_id:
|
123 |
initialize_from: null
|
124 |
load_model: false
|
125 |
resume: false
|
|
|
1 |
default_settings: null
|
2 |
behaviors:
|
3 |
+
SoccerTwos:
|
4 |
trainer_type: poca
|
5 |
hyperparameters:
|
6 |
batch_size: 2048
|
|
|
37 |
init_path: null
|
38 |
keep_checkpoints: 5
|
39 |
even_checkpoints: false
|
40 |
+
max_steps: 10000
|
41 |
time_horizon: 1000
|
42 |
summary_freq: 10000
|
43 |
threaded: false
|
44 |
self_play:
|
45 |
save_steps: 50000
|
46 |
team_change: 200000
|
47 |
+
swap_steps: 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
window: 10
|
49 |
play_against_latest_model_ratio: 0.5
|
50 |
initial_elo: 1200.0
|
|
|
70 |
no_graphics: false
|
71 |
environment_parameters: null
|
72 |
checkpoint_settings:
|
73 |
+
run_id: Soccer
|
74 |
initialize_from: null
|
75 |
load_model: false
|
76 |
resume: false
|
run_logs/timers.json
CHANGED
@@ -1,454 +1,190 @@
|
|
1 |
{
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
-
"
|
5 |
-
"value":
|
6 |
-
"min":
|
7 |
-
"max": 3.
|
8 |
-
"count":
|
9 |
-
},
|
10 |
-
"
|
11 |
-
"value":
|
12 |
-
"min":
|
13 |
-
"max":
|
14 |
-
"count":
|
15 |
-
},
|
16 |
-
"
|
17 |
-
"value":
|
18 |
-
"min":
|
19 |
-
"max":
|
20 |
-
"count":
|
21 |
-
},
|
22 |
-
"
|
23 |
-
"value":
|
24 |
-
"min":
|
25 |
-
"max":
|
26 |
-
"count":
|
27 |
-
},
|
28 |
-
"
|
29 |
-
"value":
|
30 |
-
"min":
|
31 |
-
"max":
|
32 |
-
"count":
|
33 |
-
},
|
34 |
-
"
|
35 |
-
"value":
|
36 |
-
"min":
|
37 |
-
"max":
|
38 |
-
"count":
|
39 |
-
},
|
40 |
-
"
|
41 |
-
"value":
|
42 |
-
"min":
|
43 |
-
"max":
|
44 |
-
"count":
|
45 |
-
},
|
46 |
-
"
|
47 |
-
"value":
|
48 |
-
"min":
|
49 |
-
"max":
|
50 |
-
"count":
|
51 |
-
},
|
52 |
-
"
|
53 |
-
"value":
|
54 |
-
"min":
|
55 |
-
"max": 0.
|
56 |
-
"count":
|
57 |
-
},
|
58 |
-
"
|
59 |
-
"value":
|
60 |
-
"min":
|
61 |
-
"max": 1.
|
62 |
-
"count":
|
63 |
-
},
|
64 |
-
"
|
65 |
-
"value":
|
66 |
-
"min":
|
67 |
-
"max": 0.
|
68 |
-
"count":
|
69 |
-
},
|
70 |
-
"
|
71 |
-
"value":
|
72 |
-
"min":
|
73 |
-
"max": 1.
|
74 |
-
"count":
|
75 |
-
},
|
76 |
-
"
|
77 |
-
"value": 0.
|
78 |
-
"min": 0.045828039333589865,
|
79 |
-
"max": 0.9996801018714905,
|
80 |
-
"count": 180
|
81 |
-
},
|
82 |
-
"Goalie.Environment.CumulativeReward.sum": {
|
83 |
-
"value": 10.016800398472697,
|
84 |
-
"min": 9.021400986239314,
|
85 |
-
"max": 10.917801141738892,
|
86 |
-
"count": 180
|
87 |
-
},
|
88 |
-
"Goalie.Policy.ExtrinsicReward.mean": {
|
89 |
-
"value": -0.9403761930408931,
|
90 |
-
"min": -0.954171972018536,
|
91 |
-
"max": 0.9996801018714905,
|
92 |
-
"count": 180
|
93 |
-
},
|
94 |
-
"Goalie.Policy.ExtrinsicReward.sum": {
|
95 |
-
"value": -157.98320043087006,
|
96 |
-
"min": -204.1928020119667,
|
97 |
-
"max": 9.996801018714905,
|
98 |
-
"count": 180
|
99 |
-
},
|
100 |
-
"Goalie.Environment.GroupCumulativeReward.mean": {
|
101 |
-
"value": -1.0,
|
102 |
-
"min": -1.0,
|
103 |
-
"max": 0.0,
|
104 |
-
"count": 180
|
105 |
-
},
|
106 |
-
"Goalie.Environment.GroupCumulativeReward.sum": {
|
107 |
-
"value": -168.0,
|
108 |
-
"min": -214.0,
|
109 |
-
"max": 0.0,
|
110 |
-
"count": 180
|
111 |
-
},
|
112 |
-
"Goalie.IsTraining.mean": {
|
113 |
-
"value": 1.0,
|
114 |
-
"min": 1.0,
|
115 |
-
"max": 1.0,
|
116 |
-
"count": 180
|
117 |
-
},
|
118 |
-
"Goalie.IsTraining.sum": {
|
119 |
-
"value": 1.0,
|
120 |
-
"min": 1.0,
|
121 |
-
"max": 1.0,
|
122 |
-
"count": 180
|
123 |
-
},
|
124 |
-
"Goalie.Losses.PolicyLoss.mean": {
|
125 |
-
"value": 0.016466737778197665,
|
126 |
-
"min": 0.012115506251575425,
|
127 |
-
"max": 0.02352036564067627,
|
128 |
-
"count": 86
|
129 |
-
},
|
130 |
-
"Goalie.Losses.PolicyLoss.sum": {
|
131 |
-
"value": 0.016466737778197665,
|
132 |
-
"min": 0.012115506251575425,
|
133 |
-
"max": 0.02352036564067627,
|
134 |
-
"count": 86
|
135 |
-
},
|
136 |
-
"Goalie.Losses.ValueLoss.mean": {
|
137 |
-
"value": 0.022342384917040665,
|
138 |
-
"min": 0.0004670941584966689,
|
139 |
-
"max": 0.033746559917926786,
|
140 |
-
"count": 86
|
141 |
-
},
|
142 |
-
"Goalie.Losses.ValueLoss.sum": {
|
143 |
-
"value": 0.022342384917040665,
|
144 |
-
"min": 0.0004670941584966689,
|
145 |
-
"max": 0.033746559917926786,
|
146 |
-
"count": 86
|
147 |
-
},
|
148 |
-
"Goalie.Losses.BaselineLoss.mean": {
|
149 |
-
"value": 0.02234272056569656,
|
150 |
-
"min": 0.0004670941584966689,
|
151 |
-
"max": 0.033895690863331156,
|
152 |
-
"count": 86
|
153 |
-
},
|
154 |
-
"Goalie.Losses.BaselineLoss.sum": {
|
155 |
-
"value": 0.02234272056569656,
|
156 |
-
"min": 0.0004670941584966689,
|
157 |
-
"max": 0.033895690863331156,
|
158 |
-
"count": 86
|
159 |
-
},
|
160 |
-
"Goalie.Policy.LearningRate.mean": {
|
161 |
-
"value": 0.0003,
|
162 |
-
"min": 0.0003,
|
163 |
-
"max": 0.0003,
|
164 |
-
"count": 86
|
165 |
-
},
|
166 |
-
"Goalie.Policy.LearningRate.sum": {
|
167 |
-
"value": 0.0003,
|
168 |
-
"min": 0.0003,
|
169 |
-
"max": 0.0003,
|
170 |
-
"count": 86
|
171 |
-
},
|
172 |
-
"Goalie.Policy.Epsilon.mean": {
|
173 |
-
"value": 0.20000000000000007,
|
174 |
-
"min": 0.20000000000000007,
|
175 |
-
"max": 0.20000000000000007,
|
176 |
-
"count": 86
|
177 |
-
},
|
178 |
-
"Goalie.Policy.Epsilon.sum": {
|
179 |
-
"value": 0.20000000000000007,
|
180 |
-
"min": 0.20000000000000007,
|
181 |
-
"max": 0.20000000000000007,
|
182 |
-
"count": 86
|
183 |
-
},
|
184 |
-
"Goalie.Policy.Beta.mean": {
|
185 |
-
"value": 0.005000000000000001,
|
186 |
-
"min": 0.005000000000000001,
|
187 |
-
"max": 0.005000000000000001,
|
188 |
-
"count": 86
|
189 |
-
},
|
190 |
-
"Goalie.Policy.Beta.sum": {
|
191 |
-
"value": 0.005000000000000001,
|
192 |
-
"min": 0.005000000000000001,
|
193 |
-
"max": 0.005000000000000001,
|
194 |
-
"count": 86
|
195 |
-
},
|
196 |
-
"Striker.Policy.Entropy.mean": {
|
197 |
-
"value": 2.3203654289245605,
|
198 |
-
"min": 2.2051618099212646,
|
199 |
-
"max": 3.295681953430176,
|
200 |
-
"count": 180
|
201 |
-
},
|
202 |
-
"Striker.Policy.Entropy.sum": {
|
203 |
-
"value": 23760.54296875,
|
204 |
-
"min": 15216.9345703125,
|
205 |
-
"max": 1400902.125,
|
206 |
-
"count": 180
|
207 |
-
},
|
208 |
-
"Striker.Environment.EpisodeLength.mean": {
|
209 |
-
"value": 50.415841584158414,
|
210 |
-
"min": 35.613138686131386,
|
211 |
-
"max": 999.0,
|
212 |
-
"count": 180
|
213 |
-
},
|
214 |
-
"Striker.Environment.EpisodeLength.sum": {
|
215 |
-
"value": 10184.0,
|
216 |
-
"min": 8382.0,
|
217 |
-
"max": 412654.0,
|
218 |
-
"count": 180
|
219 |
-
},
|
220 |
-
"Striker.Step.mean": {
|
221 |
-
"value": 1799842.0,
|
222 |
-
"min": 9512.0,
|
223 |
-
"max": 1799842.0,
|
224 |
-
"count": 180
|
225 |
-
},
|
226 |
-
"Striker.Step.sum": {
|
227 |
-
"value": 1799842.0,
|
228 |
-
"min": 9512.0,
|
229 |
-
"max": 1799842.0,
|
230 |
-
"count": 180
|
231 |
-
},
|
232 |
-
"Striker.Policy.ExtrinsicBaselineEstimate.mean": {
|
233 |
-
"value": 0.6013904213905334,
|
234 |
-
"min": -0.16535364091396332,
|
235 |
-
"max": 0.6533077955245972,
|
236 |
-
"count": 180
|
237 |
-
},
|
238 |
-
"Striker.Policy.ExtrinsicBaselineEstimate.sum": {
|
239 |
-
"value": 120.87947082519531,
|
240 |
-
"min": -4.340723991394043,
|
241 |
-
"max": 179.00633239746094,
|
242 |
-
"count": 180
|
243 |
-
},
|
244 |
-
"Striker.Policy.ExtrinsicValueEstimate.mean": {
|
245 |
-
"value": 0.601508378982544,
|
246 |
-
"min": -0.16497276723384857,
|
247 |
-
"max": 0.6537038087844849,
|
248 |
-
"count": 180
|
249 |
-
},
|
250 |
-
"Striker.Policy.ExtrinsicValueEstimate.sum": {
|
251 |
-
"value": 120.90318298339844,
|
252 |
-
"min": -4.237868785858154,
|
253 |
-
"max": 179.11483764648438,
|
254 |
-
"count": 180
|
255 |
-
},
|
256 |
-
"Striker.Environment.CumulativeReward.mean": {
|
257 |
-
"value": -0.04979403170094413,
|
258 |
-
"min": -0.9997200965881348,
|
259 |
-
"max": -0.035969343590448156,
|
260 |
-
"count": 180
|
261 |
-
},
|
262 |
-
"Striker.Environment.CumulativeReward.sum": {
|
263 |
-
"value": -10.00860037188977,
|
264 |
-
"min": -10.743601087480783,
|
265 |
-
"max": -9.09960101544857,
|
266 |
-
"count": 180
|
267 |
-
},
|
268 |
-
"Striker.Policy.ExtrinsicReward.mean": {
|
269 |
-
"value": 0.8502029683162917,
|
270 |
-
"min": -1.9994401931762695,
|
271 |
-
"max": 0.891693424351894,
|
272 |
-
"count": 180
|
273 |
-
},
|
274 |
-
"Striker.Policy.ExtrinsicReward.sum": {
|
275 |
-
"value": 170.89079663157463,
|
276 |
-
"min": -20.052401542663574,
|
277 |
-
"max": 244.32399827241898,
|
278 |
-
"count": 180
|
279 |
-
},
|
280 |
-
"Striker.Environment.GroupCumulativeReward.mean": {
|
281 |
-
"value": 0.949791041772757,
|
282 |
"min": 0.0,
|
283 |
-
"max": 0.
|
284 |
-
"count":
|
285 |
},
|
286 |
-
"
|
287 |
-
"value":
|
288 |
"min": 0.0,
|
289 |
-
"max":
|
290 |
-
"count":
|
291 |
-
},
|
292 |
-
"
|
293 |
-
"value":
|
294 |
-
"min":
|
295 |
-
"max":
|
296 |
-
"count":
|
297 |
-
},
|
298 |
-
"
|
299 |
-
"value":
|
300 |
-
"min":
|
301 |
-
"max":
|
302 |
-
"count":
|
303 |
-
},
|
304 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
305 |
"value": 1.0,
|
306 |
"min": 1.0,
|
307 |
"max": 1.0,
|
308 |
-
"count":
|
309 |
},
|
310 |
-
"
|
311 |
"value": 1.0,
|
312 |
"min": 1.0,
|
313 |
"max": 1.0,
|
314 |
-
"count":
|
315 |
-
},
|
316 |
-
"Striker.Losses.PolicyLoss.mean": {
|
317 |
-
"value": 0.016374270856613294,
|
318 |
-
"min": 0.011526005501703669,
|
319 |
-
"max": 0.02352414818791052,
|
320 |
-
"count": 85
|
321 |
-
},
|
322 |
-
"Striker.Losses.PolicyLoss.sum": {
|
323 |
-
"value": 0.016374270856613294,
|
324 |
-
"min": 0.011526005501703669,
|
325 |
-
"max": 0.02352414818791052,
|
326 |
-
"count": 85
|
327 |
-
},
|
328 |
-
"Striker.Losses.ValueLoss.mean": {
|
329 |
-
"value": 0.023624402284622193,
|
330 |
-
"min": 0.0006618854221111784,
|
331 |
-
"max": 0.0355209739257892,
|
332 |
-
"count": 85
|
333 |
-
},
|
334 |
-
"Striker.Losses.ValueLoss.sum": {
|
335 |
-
"value": 0.023624402284622193,
|
336 |
-
"min": 0.0006618854221111784,
|
337 |
-
"max": 0.0355209739257892,
|
338 |
-
"count": 85
|
339 |
-
},
|
340 |
-
"Striker.Losses.BaselineLoss.mean": {
|
341 |
-
"value": 0.02373644212881724,
|
342 |
-
"min": 0.0006652884049496304,
|
343 |
-
"max": 0.03594138734042644,
|
344 |
-
"count": 85
|
345 |
-
},
|
346 |
-
"Striker.Losses.BaselineLoss.sum": {
|
347 |
-
"value": 0.02373644212881724,
|
348 |
-
"min": 0.0006652884049496304,
|
349 |
-
"max": 0.03594138734042644,
|
350 |
-
"count": 85
|
351 |
-
},
|
352 |
-
"Striker.Policy.LearningRate.mean": {
|
353 |
-
"value": 0.0003,
|
354 |
-
"min": 0.0003,
|
355 |
-
"max": 0.0003,
|
356 |
-
"count": 85
|
357 |
-
},
|
358 |
-
"Striker.Policy.LearningRate.sum": {
|
359 |
-
"value": 0.0003,
|
360 |
-
"min": 0.0003,
|
361 |
-
"max": 0.0003,
|
362 |
-
"count": 85
|
363 |
-
},
|
364 |
-
"Striker.Policy.Epsilon.mean": {
|
365 |
-
"value": 0.20000000000000007,
|
366 |
-
"min": 0.20000000000000007,
|
367 |
-
"max": 0.20000000000000007,
|
368 |
-
"count": 85
|
369 |
-
},
|
370 |
-
"Striker.Policy.Epsilon.sum": {
|
371 |
-
"value": 0.20000000000000007,
|
372 |
-
"min": 0.20000000000000007,
|
373 |
-
"max": 0.20000000000000007,
|
374 |
-
"count": 85
|
375 |
-
},
|
376 |
-
"Striker.Policy.Beta.mean": {
|
377 |
-
"value": 0.005000000000000001,
|
378 |
-
"min": 0.005000000000000001,
|
379 |
-
"max": 0.005000000000000001,
|
380 |
-
"count": 85
|
381 |
-
},
|
382 |
-
"Striker.Policy.Beta.sum": {
|
383 |
-
"value": 0.005000000000000001,
|
384 |
-
"min": 0.005000000000000001,
|
385 |
-
"max": 0.005000000000000001,
|
386 |
-
"count": 85
|
387 |
}
|
388 |
},
|
389 |
"metadata": {
|
390 |
"timer_format_version": "0.1.0",
|
391 |
-
"start_time_seconds": "
|
392 |
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
|
393 |
-
"command_line_arguments": "/home/operario/anaconda3/envs/mlagents/bin/mlagents-learn
|
394 |
"mlagents_version": "1.0.0",
|
395 |
"mlagents_envs_version": "1.0.0",
|
396 |
"communication_protocol_version": "1.5.0",
|
397 |
"pytorch_version": "2.1.1+cu121",
|
398 |
"numpy_version": "1.21.2",
|
399 |
-
"end_time_seconds": "
|
400 |
},
|
401 |
-
"total":
|
402 |
"count": 1,
|
403 |
-
"self": 0.
|
404 |
"children": {
|
405 |
"run_training.setup": {
|
406 |
-
"total": 0.
|
407 |
"count": 1,
|
408 |
-
"self": 0.
|
409 |
},
|
410 |
"TrainerController.start_learning": {
|
411 |
-
"total":
|
412 |
"count": 1,
|
413 |
-
"self":
|
414 |
"children": {
|
415 |
"TrainerController._reset_env": {
|
416 |
-
"total":
|
417 |
-
"count":
|
418 |
-
"self":
|
419 |
},
|
420 |
"TrainerController.advance": {
|
421 |
-
"total":
|
422 |
-
"count":
|
423 |
-
"self":
|
424 |
"children": {
|
425 |
"env_step": {
|
426 |
-
"total":
|
427 |
-
"count":
|
428 |
-
"self":
|
429 |
"children": {
|
430 |
"SubprocessEnvManager._take_step": {
|
431 |
-
"total":
|
432 |
-
"count":
|
433 |
-
"self":
|
434 |
"children": {
|
435 |
"TorchPolicy.evaluate": {
|
436 |
-
"total":
|
437 |
-
"count":
|
438 |
-
"self":
|
439 |
}
|
440 |
}
|
441 |
},
|
442 |
"workers": {
|
443 |
-
"total":
|
444 |
-
"count":
|
445 |
"self": 0.0,
|
446 |
"children": {
|
447 |
"worker_root": {
|
448 |
-
"total":
|
449 |
-
"count":
|
450 |
"is_parallel": true,
|
451 |
-
"self":
|
452 |
"children": {
|
453 |
"run_training.setup": {
|
454 |
"total": 0.0,
|
@@ -457,48 +193,48 @@
|
|
457 |
"self": 0.0,
|
458 |
"children": {
|
459 |
"steps_from_proto": {
|
460 |
-
"total": 0.
|
461 |
"count": 2,
|
462 |
"is_parallel": true,
|
463 |
-
"self": 0.
|
464 |
"children": {
|
465 |
"_process_rank_one_or_two_observation": {
|
466 |
-
"total": 0.
|
467 |
-
"count":
|
468 |
"is_parallel": true,
|
469 |
-
"self": 0.
|
470 |
}
|
471 |
}
|
472 |
},
|
473 |
"UnityEnvironment.step": {
|
474 |
-
"total": 0.
|
475 |
"count": 1,
|
476 |
"is_parallel": true,
|
477 |
-
"self": 0.
|
478 |
"children": {
|
479 |
"UnityEnvironment._generate_step_input": {
|
480 |
-
"total": 0.
|
481 |
"count": 1,
|
482 |
"is_parallel": true,
|
483 |
-
"self": 0.
|
484 |
},
|
485 |
"communicator.exchange": {
|
486 |
-
"total": 0.
|
487 |
"count": 1,
|
488 |
"is_parallel": true,
|
489 |
-
"self": 0.
|
490 |
},
|
491 |
"steps_from_proto": {
|
492 |
-
"total": 0.
|
493 |
"count": 2,
|
494 |
"is_parallel": true,
|
495 |
-
"self": 0.
|
496 |
"children": {
|
497 |
"_process_rank_one_or_two_observation": {
|
498 |
-
"total": 0.
|
499 |
-
"count":
|
500 |
"is_parallel": true,
|
501 |
-
"self": 0.
|
502 |
}
|
503 |
}
|
504 |
}
|
@@ -507,52 +243,38 @@
|
|
507 |
}
|
508 |
},
|
509 |
"UnityEnvironment.step": {
|
510 |
-
"total":
|
511 |
-
"count":
|
512 |
"is_parallel": true,
|
513 |
-
"self":
|
514 |
"children": {
|
515 |
"UnityEnvironment._generate_step_input": {
|
516 |
-
"total":
|
517 |
-
"count":
|
518 |
"is_parallel": true,
|
519 |
-
"self":
|
520 |
},
|
521 |
"communicator.exchange": {
|
522 |
-
"total":
|
523 |
-
"count":
|
524 |
"is_parallel": true,
|
525 |
-
"self":
|
526 |
},
|
527 |
"steps_from_proto": {
|
528 |
-
"total":
|
529 |
-
"count":
|
530 |
"is_parallel": true,
|
531 |
-
"self":
|
532 |
"children": {
|
533 |
"_process_rank_one_or_two_observation": {
|
534 |
-
"total":
|
535 |
-
"count":
|
536 |
"is_parallel": true,
|
537 |
-
"self":
|
538 |
}
|
539 |
}
|
540 |
}
|
541 |
}
|
542 |
-
},
|
543 |
-
"steps_from_proto": {
|
544 |
-
"total": 0.018246098999952665,
|
545 |
-
"count": 36,
|
546 |
-
"is_parallel": true,
|
547 |
-
"self": 0.003693893993840902,
|
548 |
-
"children": {
|
549 |
-
"_process_rank_one_or_two_observation": {
|
550 |
-
"total": 0.014552205006111762,
|
551 |
-
"count": 108,
|
552 |
-
"is_parallel": true,
|
553 |
-
"self": 0.014552205006111762
|
554 |
-
}
|
555 |
-
}
|
556 |
}
|
557 |
}
|
558 |
}
|
@@ -561,47 +283,33 @@
|
|
561 |
}
|
562 |
},
|
563 |
"trainer_advance": {
|
564 |
-
"total":
|
565 |
-
"count":
|
566 |
-
"self":
|
567 |
"children": {
|
568 |
"process_trajectory": {
|
569 |
-
"total":
|
570 |
-
"count":
|
571 |
-
"self":
|
572 |
-
"children": {
|
573 |
-
"RLTrainer._checkpoint": {
|
574 |
-
"total": 0.6608758080028565,
|
575 |
-
"count": 6,
|
576 |
-
"self": 0.6608758080028565
|
577 |
-
}
|
578 |
-
}
|
579 |
-
},
|
580 |
-
"_update_policy": {
|
581 |
-
"total": 1726.2115801379887,
|
582 |
-
"count": 173,
|
583 |
-
"self": 296.8522167799774,
|
584 |
-
"children": {
|
585 |
-
"TorchPOCAOptimizer.update": {
|
586 |
-
"total": 1429.3593633580113,
|
587 |
-
"count": 5190,
|
588 |
-
"self": 1429.3593633580113
|
589 |
-
}
|
590 |
-
}
|
591 |
}
|
592 |
}
|
593 |
}
|
594 |
}
|
595 |
},
|
|
|
|
|
|
|
|
|
|
|
596 |
"TrainerController._save_models": {
|
597 |
-
"total": 0.
|
598 |
"count": 1,
|
599 |
-
"self": 0.
|
600 |
"children": {
|
601 |
"RLTrainer._checkpoint": {
|
602 |
-
"total": 0.
|
603 |
-
"count":
|
604 |
-
"self": 0.
|
605 |
}
|
606 |
}
|
607 |
}
|
|
|
1 |
{
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
+
"SoccerTwos.Policy.Entropy.mean": {
|
5 |
+
"value": 3.295698404312134,
|
6 |
+
"min": 3.295698404312134,
|
7 |
+
"max": 3.295698404312134,
|
8 |
+
"count": 1
|
9 |
+
},
|
10 |
+
"SoccerTwos.Policy.Entropy.sum": {
|
11 |
+
"value": 105462.3515625,
|
12 |
+
"min": 105462.3515625,
|
13 |
+
"max": 105462.3515625,
|
14 |
+
"count": 1
|
15 |
+
},
|
16 |
+
"SoccerTwos.Environment.EpisodeLength.mean": {
|
17 |
+
"value": 510.3,
|
18 |
+
"min": 510.3,
|
19 |
+
"max": 510.3,
|
20 |
+
"count": 1
|
21 |
+
},
|
22 |
+
"SoccerTwos.Environment.EpisodeLength.sum": {
|
23 |
+
"value": 20412.0,
|
24 |
+
"min": 20412.0,
|
25 |
+
"max": 20412.0,
|
26 |
+
"count": 1
|
27 |
+
},
|
28 |
+
"SoccerTwos.Self-play.ELO.mean": {
|
29 |
+
"value": 1198.6983882804839,
|
30 |
+
"min": 1198.6983882804839,
|
31 |
+
"max": 1198.6983882804839,
|
32 |
+
"count": 1
|
33 |
+
},
|
34 |
+
"SoccerTwos.Self-play.ELO.sum": {
|
35 |
+
"value": 16781.777435926775,
|
36 |
+
"min": 16781.777435926775,
|
37 |
+
"max": 16781.777435926775,
|
38 |
+
"count": 1
|
39 |
+
},
|
40 |
+
"SoccerTwos.Step.mean": {
|
41 |
+
"value": 9226.0,
|
42 |
+
"min": 9226.0,
|
43 |
+
"max": 9226.0,
|
44 |
+
"count": 1
|
45 |
+
},
|
46 |
+
"SoccerTwos.Step.sum": {
|
47 |
+
"value": 9226.0,
|
48 |
+
"min": 9226.0,
|
49 |
+
"max": 9226.0,
|
50 |
+
"count": 1
|
51 |
+
},
|
52 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
53 |
+
"value": 0.06891250610351562,
|
54 |
+
"min": 0.06891250610351562,
|
55 |
+
"max": 0.06891250610351562,
|
56 |
+
"count": 1
|
57 |
+
},
|
58 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
59 |
+
"value": 1.3093376159667969,
|
60 |
+
"min": 1.3093376159667969,
|
61 |
+
"max": 1.3093376159667969,
|
62 |
+
"count": 1
|
63 |
+
},
|
64 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
65 |
+
"value": 0.06894762814044952,
|
66 |
+
"min": 0.06894762814044952,
|
67 |
+
"max": 0.06894762814044952,
|
68 |
+
"count": 1
|
69 |
+
},
|
70 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
71 |
+
"value": 1.3100049495697021,
|
72 |
+
"min": 1.3100049495697021,
|
73 |
+
"max": 1.3100049495697021,
|
74 |
+
"count": 1
|
75 |
+
},
|
76 |
+
"SoccerTwos.Environment.CumulativeReward.mean": {
|
77 |
+
"value": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
"min": 0.0,
|
79 |
+
"max": 0.0,
|
80 |
+
"count": 1
|
81 |
},
|
82 |
+
"SoccerTwos.Environment.CumulativeReward.sum": {
|
83 |
+
"value": 0.0,
|
84 |
"min": 0.0,
|
85 |
+
"max": 0.0,
|
86 |
+
"count": 1
|
87 |
+
},
|
88 |
+
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
89 |
+
"value": -0.35837894991824504,
|
90 |
+
"min": -0.35837894991824504,
|
91 |
+
"max": -0.35837894991824504,
|
92 |
+
"count": 1
|
93 |
+
},
|
94 |
+
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
95 |
+
"value": -6.809200048446655,
|
96 |
+
"min": -6.809200048446655,
|
97 |
+
"max": -6.809200048446655,
|
98 |
+
"count": 1
|
99 |
+
},
|
100 |
+
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
101 |
+
"value": -0.35837894991824504,
|
102 |
+
"min": -0.35837894991824504,
|
103 |
+
"max": -0.35837894991824504,
|
104 |
+
"count": 1
|
105 |
+
},
|
106 |
+
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
107 |
+
"value": -6.809200048446655,
|
108 |
+
"min": -6.809200048446655,
|
109 |
+
"max": -6.809200048446655,
|
110 |
+
"count": 1
|
111 |
+
},
|
112 |
+
"SoccerTwos.IsTraining.mean": {
|
113 |
"value": 1.0,
|
114 |
"min": 1.0,
|
115 |
"max": 1.0,
|
116 |
+
"count": 1
|
117 |
},
|
118 |
+
"SoccerTwos.IsTraining.sum": {
|
119 |
"value": 1.0,
|
120 |
"min": 1.0,
|
121 |
"max": 1.0,
|
122 |
+
"count": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
123 |
}
|
124 |
},
|
125 |
"metadata": {
|
126 |
"timer_format_version": "0.1.0",
|
127 |
+
"start_time_seconds": "1703231750",
|
128 |
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
|
129 |
+
"command_line_arguments": "/home/operario/anaconda3/envs/mlagents/bin/mlagents-learn SoccerTwos.yaml --run-id=Soccer",
|
130 |
"mlagents_version": "1.0.0",
|
131 |
"mlagents_envs_version": "1.0.0",
|
132 |
"communication_protocol_version": "1.5.0",
|
133 |
"pytorch_version": "2.1.1+cu121",
|
134 |
"numpy_version": "1.21.2",
|
135 |
+
"end_time_seconds": "1703231769"
|
136 |
},
|
137 |
+
"total": 18.828908071000114,
|
138 |
"count": 1,
|
139 |
+
"self": 0.0038752350001232116,
|
140 |
"children": {
|
141 |
"run_training.setup": {
|
142 |
+
"total": 0.011371966999831784,
|
143 |
"count": 1,
|
144 |
+
"self": 0.011371966999831784
|
145 |
},
|
146 |
"TrainerController.start_learning": {
|
147 |
+
"total": 18.81366086900016,
|
148 |
"count": 1,
|
149 |
+
"self": 0.012658913007271622,
|
150 |
"children": {
|
151 |
"TrainerController._reset_env": {
|
152 |
+
"total": 6.519004453999969,
|
153 |
+
"count": 1,
|
154 |
+
"self": 6.519004453999969
|
155 |
},
|
156 |
"TrainerController.advance": {
|
157 |
+
"total": 12.224295807993258,
|
158 |
+
"count": 1005,
|
159 |
+
"self": 0.012754022996887215,
|
160 |
"children": {
|
161 |
"env_step": {
|
162 |
+
"total": 11.209075801001745,
|
163 |
+
"count": 1005,
|
164 |
+
"self": 9.642230745010238,
|
165 |
"children": {
|
166 |
"SubprocessEnvManager._take_step": {
|
167 |
+
"total": 1.558794789998501,
|
168 |
+
"count": 1005,
|
169 |
+
"self": 0.07714688002579351,
|
170 |
"children": {
|
171 |
"TorchPolicy.evaluate": {
|
172 |
+
"total": 1.4816479099727076,
|
173 |
+
"count": 2000,
|
174 |
+
"self": 1.4816479099727076
|
175 |
}
|
176 |
}
|
177 |
},
|
178 |
"workers": {
|
179 |
+
"total": 0.008050265993006178,
|
180 |
+
"count": 1005,
|
181 |
"self": 0.0,
|
182 |
"children": {
|
183 |
"worker_root": {
|
184 |
+
"total": 18.191109271007917,
|
185 |
+
"count": 1005,
|
186 |
"is_parallel": true,
|
187 |
+
"self": 9.978554264029299,
|
188 |
"children": {
|
189 |
"run_training.setup": {
|
190 |
"total": 0.0,
|
|
|
193 |
"self": 0.0,
|
194 |
"children": {
|
195 |
"steps_from_proto": {
|
196 |
+
"total": 0.0016817149999042158,
|
197 |
"count": 2,
|
198 |
"is_parallel": true,
|
199 |
+
"self": 0.0005443020008897292,
|
200 |
"children": {
|
201 |
"_process_rank_one_or_two_observation": {
|
202 |
+
"total": 0.0011374129990144866,
|
203 |
+
"count": 8,
|
204 |
"is_parallel": true,
|
205 |
+
"self": 0.0011374129990144866
|
206 |
}
|
207 |
}
|
208 |
},
|
209 |
"UnityEnvironment.step": {
|
210 |
+
"total": 0.0247552379996705,
|
211 |
"count": 1,
|
212 |
"is_parallel": true,
|
213 |
+
"self": 0.0005118170001878752,
|
214 |
"children": {
|
215 |
"UnityEnvironment._generate_step_input": {
|
216 |
+
"total": 0.0006443479996960377,
|
217 |
"count": 1,
|
218 |
"is_parallel": true,
|
219 |
+
"self": 0.0006443479996960377
|
220 |
},
|
221 |
"communicator.exchange": {
|
222 |
+
"total": 0.02191044499977579,
|
223 |
"count": 1,
|
224 |
"is_parallel": true,
|
225 |
+
"self": 0.02191044499977579
|
226 |
},
|
227 |
"steps_from_proto": {
|
228 |
+
"total": 0.0016886280000107945,
|
229 |
"count": 2,
|
230 |
"is_parallel": true,
|
231 |
+
"self": 0.0003622190006353776,
|
232 |
"children": {
|
233 |
"_process_rank_one_or_two_observation": {
|
234 |
+
"total": 0.001326408999375417,
|
235 |
+
"count": 8,
|
236 |
"is_parallel": true,
|
237 |
+
"self": 0.001326408999375417
|
238 |
}
|
239 |
}
|
240 |
}
|
|
|
243 |
}
|
244 |
},
|
245 |
"UnityEnvironment.step": {
|
246 |
+
"total": 8.212555006978619,
|
247 |
+
"count": 1004,
|
248 |
"is_parallel": true,
|
249 |
+
"self": 0.3458426219631292,
|
250 |
"children": {
|
251 |
"UnityEnvironment._generate_step_input": {
|
252 |
+
"total": 0.20143538798947702,
|
253 |
+
"count": 1004,
|
254 |
"is_parallel": true,
|
255 |
+
"self": 0.20143538798947702
|
256 |
},
|
257 |
"communicator.exchange": {
|
258 |
+
"total": 6.67237666901201,
|
259 |
+
"count": 1004,
|
260 |
"is_parallel": true,
|
261 |
+
"self": 6.67237666901201
|
262 |
},
|
263 |
"steps_from_proto": {
|
264 |
+
"total": 0.9929003280140023,
|
265 |
+
"count": 2008,
|
266 |
"is_parallel": true,
|
267 |
+
"self": 0.18314762201407575,
|
268 |
"children": {
|
269 |
"_process_rank_one_or_two_observation": {
|
270 |
+
"total": 0.8097527059999265,
|
271 |
+
"count": 8032,
|
272 |
"is_parallel": true,
|
273 |
+
"self": 0.8097527059999265
|
274 |
}
|
275 |
}
|
276 |
}
|
277 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
278 |
}
|
279 |
}
|
280 |
}
|
|
|
283 |
}
|
284 |
},
|
285 |
"trainer_advance": {
|
286 |
+
"total": 1.0024659839946253,
|
287 |
+
"count": 1005,
|
288 |
+
"self": 0.05726587000845029,
|
289 |
"children": {
|
290 |
"process_trajectory": {
|
291 |
+
"total": 0.945200113986175,
|
292 |
+
"count": 1005,
|
293 |
+
"self": 0.945200113986175
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
294 |
}
|
295 |
}
|
296 |
}
|
297 |
}
|
298 |
},
|
299 |
+
"trainer_threads": {
|
300 |
+
"total": 6.089994712965563e-07,
|
301 |
+
"count": 1,
|
302 |
+
"self": 6.089994712965563e-07
|
303 |
+
},
|
304 |
"TrainerController._save_models": {
|
305 |
+
"total": 0.05770108500018978,
|
306 |
"count": 1,
|
307 |
+
"self": 0.0008857650000209105,
|
308 |
"children": {
|
309 |
"RLTrainer._checkpoint": {
|
310 |
+
"total": 0.05681532000016887,
|
311 |
+
"count": 1,
|
312 |
+
"self": 0.05681532000016887
|
313 |
}
|
314 |
}
|
315 |
}
|
run_logs/training_status.json
CHANGED
@@ -1,101 +1,24 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
3 |
"checkpoints": [
|
4 |
{
|
5 |
-
"steps":
|
6 |
-
"file_path": "results/
|
7 |
-
"reward": 0.
|
8 |
-
"creation_time":
|
9 |
"auxillary_file_paths": [
|
10 |
-
"results/
|
11 |
-
]
|
12 |
-
},
|
13 |
-
{
|
14 |
-
"steps": 999974,
|
15 |
-
"file_path": "results/Proba/Goalie/Goalie-999974.onnx",
|
16 |
-
"reward": 0.3689773957824932,
|
17 |
-
"creation_time": 1702977402.499321,
|
18 |
-
"auxillary_file_paths": [
|
19 |
-
"results/Proba/Goalie/Goalie-999974.pt"
|
20 |
-
]
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"steps": 1499980,
|
24 |
-
"file_path": "results/Proba/Goalie/Goalie-1499980.onnx",
|
25 |
-
"reward": 0.042800000247855984,
|
26 |
-
"creation_time": 1702979254.7808285,
|
27 |
-
"auxillary_file_paths": [
|
28 |
-
"results/Proba/Goalie/Goalie-1499980.pt"
|
29 |
-
]
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"steps": 1807818,
|
33 |
-
"file_path": "results/Proba/Goalie/Goalie-1807818.onnx",
|
34 |
-
"reward": null,
|
35 |
-
"creation_time": 1702980564.4739382,
|
36 |
-
"auxillary_file_paths": [
|
37 |
-
"results/Proba/Goalie/Goalie-1807818.pt"
|
38 |
-
]
|
39 |
-
}
|
40 |
-
],
|
41 |
-
"elo": 771.3258240415493,
|
42 |
-
"final_checkpoint": {
|
43 |
-
"steps": 1807818,
|
44 |
-
"file_path": "results/Proba/Goalie.onnx",
|
45 |
-
"reward": null,
|
46 |
-
"creation_time": 1702980564.4739382,
|
47 |
-
"auxillary_file_paths": [
|
48 |
-
"results/Proba/Goalie/Goalie-1807818.pt"
|
49 |
-
]
|
50 |
-
}
|
51 |
-
},
|
52 |
-
"Striker": {
|
53 |
-
"checkpoints": [
|
54 |
-
{
|
55 |
-
"steps": 499317,
|
56 |
-
"file_path": "results/Proba/Striker/Striker-499317.onnx",
|
57 |
-
"reward": -0.5727692818125854,
|
58 |
-
"creation_time": 1702976347.5755029,
|
59 |
-
"auxillary_file_paths": [
|
60 |
-
"results/Proba/Striker/Striker-499317.pt"
|
61 |
-
]
|
62 |
-
},
|
63 |
-
{
|
64 |
-
"steps": 999985,
|
65 |
-
"file_path": "results/Proba/Striker/Striker-999985.onnx",
|
66 |
-
"reward": -0.07280247349200057,
|
67 |
-
"creation_time": 1702977703.5105634,
|
68 |
-
"auxillary_file_paths": [
|
69 |
-
"results/Proba/Striker/Striker-999985.pt"
|
70 |
-
]
|
71 |
-
},
|
72 |
-
{
|
73 |
-
"steps": 1499979,
|
74 |
-
"file_path": "results/Proba/Striker/Striker-1499979.onnx",
|
75 |
-
"reward": -0.05407068019914896,
|
76 |
-
"creation_time": 1702979607.5258744,
|
77 |
-
"auxillary_file_paths": [
|
78 |
-
"results/Proba/Striker/Striker-1499979.pt"
|
79 |
-
]
|
80 |
-
},
|
81 |
-
{
|
82 |
-
"steps": 1802718,
|
83 |
-
"file_path": "results/Proba/Striker/Striker-1802718.onnx",
|
84 |
-
"reward": -0.03104210407228062,
|
85 |
-
"creation_time": 1702980564.5476835,
|
86 |
-
"auxillary_file_paths": [
|
87 |
-
"results/Proba/Striker/Striker-1802718.pt"
|
88 |
]
|
89 |
}
|
90 |
],
|
91 |
-
"elo": 1755.7615527828686,
|
92 |
"final_checkpoint": {
|
93 |
-
"steps":
|
94 |
-
"file_path": "results/
|
95 |
-
"reward":
|
96 |
-
"creation_time":
|
97 |
"auxillary_file_paths": [
|
98 |
-
"results/
|
99 |
]
|
100 |
}
|
101 |
},
|
|
|
1 |
{
|
2 |
+
"SoccerTwos": {
|
3 |
+
"elo": 1197.0439391453008,
|
4 |
"checkpoints": [
|
5 |
{
|
6 |
+
"steps": 10226,
|
7 |
+
"file_path": "results/Soccer/SoccerTwos/SoccerTwos-10226.onnx",
|
8 |
+
"reward": 0.0,
|
9 |
+
"creation_time": 1703231769.47281,
|
10 |
"auxillary_file_paths": [
|
11 |
+
"results/Soccer/SoccerTwos/SoccerTwos-10226.pt"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
]
|
13 |
}
|
14 |
],
|
|
|
15 |
"final_checkpoint": {
|
16 |
+
"steps": 10226,
|
17 |
+
"file_path": "results/Soccer/SoccerTwos.onnx",
|
18 |
+
"reward": 0.0,
|
19 |
+
"creation_time": 1703231769.47281,
|
20 |
"auxillary_file_paths": [
|
21 |
+
"results/Soccer/SoccerTwos/SoccerTwos-10226.pt"
|
22 |
]
|
23 |
}
|
24 |
},
|