Commit
•
0b736ca
1
Parent(s):
808f18c
First Push
Browse files- README.md +31 -0
- SoccerTwos.onnx +3 -0
- SoccerTwos/SoccerTwos-16999758.onnx +3 -0
- SoccerTwos/SoccerTwos-16999758.pt +3 -0
- SoccerTwos/SoccerTwos-17499362.onnx +3 -0
- SoccerTwos/SoccerTwos-17499362.pt +3 -0
- SoccerTwos/SoccerTwos-17999098.onnx +3 -0
- SoccerTwos/SoccerTwos-17999098.pt +3 -0
- SoccerTwos/SoccerTwos-18499702.onnx +3 -0
- SoccerTwos/SoccerTwos-18499702.pt +3 -0
- SoccerTwos/SoccerTwos-18630702.onnx +3 -0
- SoccerTwos/SoccerTwos-18630702.pt +3 -0
- SoccerTwos/checkpoint.pt +3 -0
- SoccerTwos/events.out.tfevents.1684099444.DESKTOP-M2HS072.18156.0 +3 -0
- config.json +1 -0
- configuration.yaml +81 -0
- run_logs/Player-0.log +0 -0
- run_logs/timers.json +375 -0
- run_logs/training_status.json +66 -0
README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- unity-ml-agents
|
5 |
+
- ml-agents
|
6 |
+
- deep-reinforcement-learning
|
7 |
+
- reinforcement-learning
|
8 |
+
- ML-Agents-SoccerTwos
|
9 |
+
library_name: ml-agents
|
10 |
+
---
|
11 |
+
|
12 |
+
# **poca** Agent playing **SoccerTwos**
|
13 |
+
This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
|
14 |
+
|
15 |
+
## Usage (with ML-Agents)
|
16 |
+
The Documentation: https://github.com/huggingface/ml-agents#get-started
|
17 |
+
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
|
18 |
+
|
19 |
+
|
20 |
+
### Resume the training
|
21 |
+
```
|
22 |
+
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
|
23 |
+
```
|
24 |
+
### Watch your Agent play
|
25 |
+
You can watch your agent **playing directly in your browser:**.
|
26 |
+
|
27 |
+
1. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
|
28 |
+
2. Step 1: Write your model_id: JoBuettner/poca-SoccerTwos
|
29 |
+
3. Step 2: Select your *.nn /*.onnx file
|
30 |
+
4. Click on Watch the agent play 👀
|
31 |
+
|
SoccerTwos.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1251d2ea42a7531014f41f51782edd7f4f29f0adb4202e5c16ee18b31758b9a2
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-16999758.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a108cf7b4f83b8aacebbbcd8108234d5af78b2769bd9e68f4f18faa357b2b41b
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-16999758.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a055099eaf7645b50f14c95c3ff698a739a235f5c77ca9a0e31eb3fb748ce108
|
3 |
+
size 28430025
|
SoccerTwos/SoccerTwos-17499362.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:735484ccb59e530987562eb09f52b91ea7656c5e9e4074fdefdf7c1431c482b5
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-17499362.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38682901875dc527dea757f1330105d7470408f7b7e82a9ecb989d0aa3946a3a
|
3 |
+
size 28430025
|
SoccerTwos/SoccerTwos-17999098.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a553e06a91c13a419cc2f575a3737f4cc7e5ccf6187278824a705302569e85e
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-17999098.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f0316433429abbbb22b6426b4f9a29edee9d3355f52d484c8e5304b53203d16
|
3 |
+
size 28430025
|
SoccerTwos/SoccerTwos-18499702.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daf84907c766ef87ed87889a5e30bb3c339c3d4485ce40a4aecb472755736430
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-18499702.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44027caab51636b8f13e48a7ea31ccad740b38093f6d0554ea14c192b5318aa6
|
3 |
+
size 28430025
|
SoccerTwos/SoccerTwos-18630702.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1251d2ea42a7531014f41f51782edd7f4f29f0adb4202e5c16ee18b31758b9a2
|
3 |
+
size 1768747
|
SoccerTwos/SoccerTwos-18630702.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25cc2196878f2d7e707ea4ec1c7e813ff12448c2df7ff570a11ff60ec25aa601
|
3 |
+
size 28430025
|
SoccerTwos/checkpoint.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:067458abfa4fe3a7187ca2cb62b5e934e809a1f8c7c05801bc498412ad97587d
|
3 |
+
size 28428927
|
SoccerTwos/events.out.tfevents.1684099444.DESKTOP-M2HS072.18156.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3771d5c233ddb9527835baf6d1cc093c2115545ebb4131154c9e9ccf291377d
|
3 |
+
size 3091205
|
config.json
ADDED
@@ -0,0 +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"}, "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, "checkpoint_interval": 500000, "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.exe", "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": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
|
configuration.yaml
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
default_settings: null
|
2 |
+
behaviors:
|
3 |
+
SoccerTwos:
|
4 |
+
trainer_type: poca
|
5 |
+
hyperparameters:
|
6 |
+
batch_size: 2048
|
7 |
+
buffer_size: 20480
|
8 |
+
learning_rate: 0.0003
|
9 |
+
beta: 0.005
|
10 |
+
epsilon: 0.2
|
11 |
+
lambd: 0.95
|
12 |
+
num_epoch: 3
|
13 |
+
learning_rate_schedule: constant
|
14 |
+
beta_schedule: constant
|
15 |
+
epsilon_schedule: constant
|
16 |
+
network_settings:
|
17 |
+
normalize: false
|
18 |
+
hidden_units: 512
|
19 |
+
num_layers: 2
|
20 |
+
vis_encode_type: simple
|
21 |
+
memory: null
|
22 |
+
goal_conditioning_type: hyper
|
23 |
+
deterministic: false
|
24 |
+
reward_signals:
|
25 |
+
extrinsic:
|
26 |
+
gamma: 0.99
|
27 |
+
strength: 1.0
|
28 |
+
network_settings:
|
29 |
+
normalize: false
|
30 |
+
hidden_units: 128
|
31 |
+
num_layers: 2
|
32 |
+
vis_encode_type: simple
|
33 |
+
memory: null
|
34 |
+
goal_conditioning_type: hyper
|
35 |
+
deterministic: false
|
36 |
+
init_path: null
|
37 |
+
keep_checkpoints: 5
|
38 |
+
checkpoint_interval: 500000
|
39 |
+
max_steps: 50000000
|
40 |
+
time_horizon: 1000
|
41 |
+
summary_freq: 10000
|
42 |
+
threaded: false
|
43 |
+
self_play:
|
44 |
+
save_steps: 50000
|
45 |
+
team_change: 200000
|
46 |
+
swap_steps: 2000
|
47 |
+
window: 10
|
48 |
+
play_against_latest_model_ratio: 0.5
|
49 |
+
initial_elo: 1200.0
|
50 |
+
behavioral_cloning: null
|
51 |
+
env_settings:
|
52 |
+
env_path: .\training-envs-executables\SoccerTwos.exe
|
53 |
+
env_args: null
|
54 |
+
base_port: 5005
|
55 |
+
num_envs: 1
|
56 |
+
num_areas: 1
|
57 |
+
seed: -1
|
58 |
+
max_lifetime_restarts: 10
|
59 |
+
restarts_rate_limit_n: 1
|
60 |
+
restarts_rate_limit_period_s: 60
|
61 |
+
engine_settings:
|
62 |
+
width: 84
|
63 |
+
height: 84
|
64 |
+
quality_level: 5
|
65 |
+
time_scale: 20
|
66 |
+
target_frame_rate: -1
|
67 |
+
capture_frame_rate: 60
|
68 |
+
no_graphics: true
|
69 |
+
environment_parameters: null
|
70 |
+
checkpoint_settings:
|
71 |
+
run_id: SoccerTwos
|
72 |
+
initialize_from: null
|
73 |
+
load_model: false
|
74 |
+
resume: false
|
75 |
+
force: true
|
76 |
+
train_model: false
|
77 |
+
inference: false
|
78 |
+
results_dir: results
|
79 |
+
torch_settings:
|
80 |
+
device: null
|
81 |
+
debug: false
|
run_logs/Player-0.log
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run_logs/timers.json
ADDED
@@ -0,0 +1,375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"name": "root",
|
3 |
+
"gauges": {
|
4 |
+
"SoccerTwos.Policy.Entropy.mean": {
|
5 |
+
"value": 1.954332947731018,
|
6 |
+
"min": 1.3264840841293335,
|
7 |
+
"max": 3.295761823654175,
|
8 |
+
"count": 1863
|
9 |
+
},
|
10 |
+
"SoccerTwos.Policy.Entropy.sum": {
|
11 |
+
"value": 37022.8828125,
|
12 |
+
"min": 13968.203125,
|
13 |
+
"max": 119658.234375,
|
14 |
+
"count": 1863
|
15 |
+
},
|
16 |
+
"SoccerTwos.Environment.EpisodeLength.mean": {
|
17 |
+
"value": 999.0,
|
18 |
+
"min": 407.6666666666667,
|
19 |
+
"max": 999.0,
|
20 |
+
"count": 1863
|
21 |
+
},
|
22 |
+
"SoccerTwos.Environment.EpisodeLength.sum": {
|
23 |
+
"value": 19980.0,
|
24 |
+
"min": 4120.0,
|
25 |
+
"max": 29364.0,
|
26 |
+
"count": 1863
|
27 |
+
},
|
28 |
+
"SoccerTwos.Self-play.ELO.mean": {
|
29 |
+
"value": 1193.01010444665,
|
30 |
+
"min": 1183.7567493884217,
|
31 |
+
"max": 1211.300011561075,
|
32 |
+
"count": 221
|
33 |
+
},
|
34 |
+
"SoccerTwos.Self-play.ELO.sum": {
|
35 |
+
"value": 2386.0202088933,
|
36 |
+
"min": 2368.8649997466773,
|
37 |
+
"max": 14529.666804347418,
|
38 |
+
"count": 221
|
39 |
+
},
|
40 |
+
"SoccerTwos.Step.mean": {
|
41 |
+
"value": 18629702.0,
|
42 |
+
"min": 9616.0,
|
43 |
+
"max": 18629702.0,
|
44 |
+
"count": 1863
|
45 |
+
},
|
46 |
+
"SoccerTwos.Step.sum": {
|
47 |
+
"value": 18629702.0,
|
48 |
+
"min": 9616.0,
|
49 |
+
"max": 18629702.0,
|
50 |
+
"count": 1863
|
51 |
+
},
|
52 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
53 |
+
"value": -1.111352389671083e-06,
|
54 |
+
"min": -0.044144924730062485,
|
55 |
+
"max": 0.018055004999041557,
|
56 |
+
"count": 1863
|
57 |
+
},
|
58 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
59 |
+
"value": -1.1113524124084506e-05,
|
60 |
+
"min": -0.662173867225647,
|
61 |
+
"max": 0.25595420598983765,
|
62 |
+
"count": 1863
|
63 |
+
},
|
64 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
65 |
+
"value": -3.35992376676586e-06,
|
66 |
+
"min": -0.04418877512216568,
|
67 |
+
"max": 0.01754818670451641,
|
68 |
+
"count": 1863
|
69 |
+
},
|
70 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
71 |
+
"value": -3.359923721291125e-05,
|
72 |
+
"min": -0.6628316044807434,
|
73 |
+
"max": 0.2481795847415924,
|
74 |
+
"count": 1863
|
75 |
+
},
|
76 |
+
"SoccerTwos.Environment.CumulativeReward.mean": {
|
77 |
+
"value": 0.0,
|
78 |
+
"min": 0.0,
|
79 |
+
"max": 0.0,
|
80 |
+
"count": 1863
|
81 |
+
},
|
82 |
+
"SoccerTwos.Environment.CumulativeReward.sum": {
|
83 |
+
"value": 0.0,
|
84 |
+
"min": 0.0,
|
85 |
+
"max": 0.0,
|
86 |
+
"count": 1863
|
87 |
+
},
|
88 |
+
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
89 |
+
"value": 0.0,
|
90 |
+
"min": -0.5,
|
91 |
+
"max": 0.3054000011512211,
|
92 |
+
"count": 1863
|
93 |
+
},
|
94 |
+
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
95 |
+
"value": 0.0,
|
96 |
+
"min": -8.0,
|
97 |
+
"max": 4.275600016117096,
|
98 |
+
"count": 1863
|
99 |
+
},
|
100 |
+
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
101 |
+
"value": 0.0,
|
102 |
+
"min": -0.5,
|
103 |
+
"max": 0.3054000011512211,
|
104 |
+
"count": 1863
|
105 |
+
},
|
106 |
+
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
107 |
+
"value": 0.0,
|
108 |
+
"min": -8.0,
|
109 |
+
"max": 4.275600016117096,
|
110 |
+
"count": 1863
|
111 |
+
},
|
112 |
+
"SoccerTwos.IsTraining.mean": {
|
113 |
+
"value": 1.0,
|
114 |
+
"min": 1.0,
|
115 |
+
"max": 1.0,
|
116 |
+
"count": 1863
|
117 |
+
},
|
118 |
+
"SoccerTwos.IsTraining.sum": {
|
119 |
+
"value": 1.0,
|
120 |
+
"min": 1.0,
|
121 |
+
"max": 1.0,
|
122 |
+
"count": 1863
|
123 |
+
},
|
124 |
+
"SoccerTwos.Losses.PolicyLoss.mean": {
|
125 |
+
"value": 0.01567243464984737,
|
126 |
+
"min": 0.010860774454098039,
|
127 |
+
"max": 0.027968196836688244,
|
128 |
+
"count": 851
|
129 |
+
},
|
130 |
+
"SoccerTwos.Losses.PolicyLoss.sum": {
|
131 |
+
"value": 0.01567243464984737,
|
132 |
+
"min": 0.010860774454098039,
|
133 |
+
"max": 0.027968196836688244,
|
134 |
+
"count": 851
|
135 |
+
},
|
136 |
+
"SoccerTwos.Losses.ValueLoss.mean": {
|
137 |
+
"value": 3.425246914804762e-11,
|
138 |
+
"min": 2.3595142737790433e-11,
|
139 |
+
"max": 0.005436938970039288,
|
140 |
+
"count": 851
|
141 |
+
},
|
142 |
+
"SoccerTwos.Losses.ValueLoss.sum": {
|
143 |
+
"value": 3.425246914804762e-11,
|
144 |
+
"min": 2.3595142737790433e-11,
|
145 |
+
"max": 0.005436938970039288,
|
146 |
+
"count": 851
|
147 |
+
},
|
148 |
+
"SoccerTwos.Losses.BaselineLoss.mean": {
|
149 |
+
"value": 4.56346413204208e-11,
|
150 |
+
"min": 3.366520314832903e-11,
|
151 |
+
"max": 0.005439961049705744,
|
152 |
+
"count": 851
|
153 |
+
},
|
154 |
+
"SoccerTwos.Losses.BaselineLoss.sum": {
|
155 |
+
"value": 4.56346413204208e-11,
|
156 |
+
"min": 3.366520314832903e-11,
|
157 |
+
"max": 0.005439961049705744,
|
158 |
+
"count": 851
|
159 |
+
},
|
160 |
+
"SoccerTwos.Policy.LearningRate.mean": {
|
161 |
+
"value": 0.0003,
|
162 |
+
"min": 0.0003,
|
163 |
+
"max": 0.0003,
|
164 |
+
"count": 851
|
165 |
+
},
|
166 |
+
"SoccerTwos.Policy.LearningRate.sum": {
|
167 |
+
"value": 0.0003,
|
168 |
+
"min": 0.0003,
|
169 |
+
"max": 0.0003,
|
170 |
+
"count": 851
|
171 |
+
},
|
172 |
+
"SoccerTwos.Policy.Epsilon.mean": {
|
173 |
+
"value": 0.20000000000000007,
|
174 |
+
"min": 0.19999999999999996,
|
175 |
+
"max": 0.20000000000000007,
|
176 |
+
"count": 851
|
177 |
+
},
|
178 |
+
"SoccerTwos.Policy.Epsilon.sum": {
|
179 |
+
"value": 0.20000000000000007,
|
180 |
+
"min": 0.19999999999999996,
|
181 |
+
"max": 0.20000000000000007,
|
182 |
+
"count": 851
|
183 |
+
},
|
184 |
+
"SoccerTwos.Policy.Beta.mean": {
|
185 |
+
"value": 0.005000000000000001,
|
186 |
+
"min": 0.005,
|
187 |
+
"max": 0.005000000000000001,
|
188 |
+
"count": 851
|
189 |
+
},
|
190 |
+
"SoccerTwos.Policy.Beta.sum": {
|
191 |
+
"value": 0.005000000000000001,
|
192 |
+
"min": 0.005,
|
193 |
+
"max": 0.005000000000000001,
|
194 |
+
"count": 851
|
195 |
+
}
|
196 |
+
},
|
197 |
+
"metadata": {
|
198 |
+
"timer_format_version": "0.1.0",
|
199 |
+
"start_time_seconds": "1684099442",
|
200 |
+
"python_version": "3.7.9 (tags/v3.7.9:13c94747c7, Aug 17 2020, 18:58:18) [MSC v.1900 64 bit (AMD64)]",
|
201 |
+
"command_line_arguments": "C:\\Users\\johbu\\AppData\\Local\\Programs\\Python\\Python37\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=.\\training-envs-executables\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
|
202 |
+
"mlagents_version": "0.29.0.dev0",
|
203 |
+
"mlagents_envs_version": "0.29.0.dev0",
|
204 |
+
"communication_protocol_version": "1.5.0",
|
205 |
+
"pytorch_version": "1.13.1+cpu",
|
206 |
+
"numpy_version": "1.21.6",
|
207 |
+
"end_time_seconds": "1684141538"
|
208 |
+
},
|
209 |
+
"total": 42095.9810893,
|
210 |
+
"count": 1,
|
211 |
+
"self": 0.40295310000510653,
|
212 |
+
"children": {
|
213 |
+
"run_training.setup": {
|
214 |
+
"total": 0.07414120000000013,
|
215 |
+
"count": 1,
|
216 |
+
"self": 0.07414120000000013
|
217 |
+
},
|
218 |
+
"TrainerController.start_learning": {
|
219 |
+
"total": 42095.503995,
|
220 |
+
"count": 1,
|
221 |
+
"self": 14.704631397704361,
|
222 |
+
"children": {
|
223 |
+
"TrainerController._reset_env": {
|
224 |
+
"total": 8.012174899989207,
|
225 |
+
"count": 93,
|
226 |
+
"self": 8.012174899989207
|
227 |
+
},
|
228 |
+
"TrainerController.advance": {
|
229 |
+
"total": 42072.67401290231,
|
230 |
+
"count": 1217474,
|
231 |
+
"self": 15.07942959882348,
|
232 |
+
"children": {
|
233 |
+
"env_step": {
|
234 |
+
"total": 13986.828992203496,
|
235 |
+
"count": 1217474,
|
236 |
+
"self": 11024.74603840562,
|
237 |
+
"children": {
|
238 |
+
"SubprocessEnvManager._take_step": {
|
239 |
+
"total": 2952.9800428989524,
|
240 |
+
"count": 1217474,
|
241 |
+
"self": 85.42414060606143,
|
242 |
+
"children": {
|
243 |
+
"TorchPolicy.evaluate": {
|
244 |
+
"total": 2867.555902292891,
|
245 |
+
"count": 2417620,
|
246 |
+
"self": 391.39378209354527,
|
247 |
+
"children": {
|
248 |
+
"TorchPolicy.sample_actions": {
|
249 |
+
"total": 2476.1621201993457,
|
250 |
+
"count": 2417620,
|
251 |
+
"self": 2476.1621201993457
|
252 |
+
}
|
253 |
+
}
|
254 |
+
}
|
255 |
+
}
|
256 |
+
},
|
257 |
+
"workers": {
|
258 |
+
"total": 9.102910898924563,
|
259 |
+
"count": 1217474,
|
260 |
+
"self": 0.0,
|
261 |
+
"children": {
|
262 |
+
"worker_root": {
|
263 |
+
"total": 42069.48677810002,
|
264 |
+
"count": 1217474,
|
265 |
+
"is_parallel": true,
|
266 |
+
"self": 33182.724791397326,
|
267 |
+
"children": {
|
268 |
+
"steps_from_proto": {
|
269 |
+
"total": 0.13034849997127318,
|
270 |
+
"count": 186,
|
271 |
+
"is_parallel": true,
|
272 |
+
"self": 0.029093799915881124,
|
273 |
+
"children": {
|
274 |
+
"_process_rank_one_or_two_observation": {
|
275 |
+
"total": 0.10125470005539206,
|
276 |
+
"count": 744,
|
277 |
+
"is_parallel": true,
|
278 |
+
"self": 0.10125470005539206
|
279 |
+
}
|
280 |
+
}
|
281 |
+
},
|
282 |
+
"UnityEnvironment.step": {
|
283 |
+
"total": 8886.63163820272,
|
284 |
+
"count": 1217474,
|
285 |
+
"is_parallel": true,
|
286 |
+
"self": 504.76745889585254,
|
287 |
+
"children": {
|
288 |
+
"UnityEnvironment._generate_step_input": {
|
289 |
+
"total": 474.3629797996917,
|
290 |
+
"count": 1217474,
|
291 |
+
"is_parallel": true,
|
292 |
+
"self": 474.3629797996917
|
293 |
+
},
|
294 |
+
"communicator.exchange": {
|
295 |
+
"total": 6278.15898090307,
|
296 |
+
"count": 1217474,
|
297 |
+
"is_parallel": true,
|
298 |
+
"self": 6278.15898090307
|
299 |
+
},
|
300 |
+
"steps_from_proto": {
|
301 |
+
"total": 1629.3422186041057,
|
302 |
+
"count": 2434948,
|
303 |
+
"is_parallel": true,
|
304 |
+
"self": 348.5505115046576,
|
305 |
+
"children": {
|
306 |
+
"_process_rank_one_or_two_observation": {
|
307 |
+
"total": 1280.791707099448,
|
308 |
+
"count": 9739792,
|
309 |
+
"is_parallel": true,
|
310 |
+
"self": 1280.791707099448
|
311 |
+
}
|
312 |
+
}
|
313 |
+
}
|
314 |
+
}
|
315 |
+
}
|
316 |
+
}
|
317 |
+
}
|
318 |
+
}
|
319 |
+
}
|
320 |
+
}
|
321 |
+
},
|
322 |
+
"trainer_advance": {
|
323 |
+
"total": 28070.76559109999,
|
324 |
+
"count": 1217474,
|
325 |
+
"self": 157.3080017994107,
|
326 |
+
"children": {
|
327 |
+
"process_trajectory": {
|
328 |
+
"total": 3583.9044986006,
|
329 |
+
"count": 1217474,
|
330 |
+
"self": 3580.662047500574,
|
331 |
+
"children": {
|
332 |
+
"RLTrainer._checkpoint": {
|
333 |
+
"total": 3.2424511000260736,
|
334 |
+
"count": 37,
|
335 |
+
"self": 3.2424511000260736
|
336 |
+
}
|
337 |
+
}
|
338 |
+
},
|
339 |
+
"_update_policy": {
|
340 |
+
"total": 24329.553090699977,
|
341 |
+
"count": 851,
|
342 |
+
"self": 1843.207980099789,
|
343 |
+
"children": {
|
344 |
+
"TorchPOCAOptimizer.update": {
|
345 |
+
"total": 22486.34511060019,
|
346 |
+
"count": 25542,
|
347 |
+
"self": 22486.34511060019
|
348 |
+
}
|
349 |
+
}
|
350 |
+
}
|
351 |
+
}
|
352 |
+
}
|
353 |
+
}
|
354 |
+
},
|
355 |
+
"trainer_threads": {
|
356 |
+
"total": 7.999988156370819e-07,
|
357 |
+
"count": 1,
|
358 |
+
"self": 7.999988156370819e-07
|
359 |
+
},
|
360 |
+
"TrainerController._save_models": {
|
361 |
+
"total": 0.11317499999859137,
|
362 |
+
"count": 1,
|
363 |
+
"self": 0.029603699993458577,
|
364 |
+
"children": {
|
365 |
+
"RLTrainer._checkpoint": {
|
366 |
+
"total": 0.0835713000051328,
|
367 |
+
"count": 1,
|
368 |
+
"self": 0.0835713000051328
|
369 |
+
}
|
370 |
+
}
|
371 |
+
}
|
372 |
+
}
|
373 |
+
}
|
374 |
+
}
|
375 |
+
}
|
run_logs/training_status.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"SoccerTwos": {
|
3 |
+
"checkpoints": [
|
4 |
+
{
|
5 |
+
"steps": 16999758,
|
6 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-16999758.onnx",
|
7 |
+
"reward": 0.0,
|
8 |
+
"creation_time": 1684137871.4929845,
|
9 |
+
"auxillary_file_paths": [
|
10 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-16999758.pt"
|
11 |
+
]
|
12 |
+
},
|
13 |
+
{
|
14 |
+
"steps": 17499362,
|
15 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-17499362.onnx",
|
16 |
+
"reward": 0.0,
|
17 |
+
"creation_time": 1684138996.7285898,
|
18 |
+
"auxillary_file_paths": [
|
19 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-17499362.pt"
|
20 |
+
]
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"steps": 17999098,
|
24 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-17999098.onnx",
|
25 |
+
"reward": 0.0,
|
26 |
+
"creation_time": 1684140098.2895796,
|
27 |
+
"auxillary_file_paths": [
|
28 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-17999098.pt"
|
29 |
+
]
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"steps": 18499702,
|
33 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18499702.onnx",
|
34 |
+
"reward": 0.0,
|
35 |
+
"creation_time": 1684141242.3639696,
|
36 |
+
"auxillary_file_paths": [
|
37 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18499702.pt"
|
38 |
+
]
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"steps": 18630702,
|
42 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18630702.onnx",
|
43 |
+
"reward": 0.0,
|
44 |
+
"creation_time": 1684141538.436475,
|
45 |
+
"auxillary_file_paths": [
|
46 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18630702.pt"
|
47 |
+
]
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"elo": 1193.01010444665,
|
51 |
+
"final_checkpoint": {
|
52 |
+
"steps": 18630702,
|
53 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
|
54 |
+
"reward": 0.0,
|
55 |
+
"creation_time": 1684141538.436475,
|
56 |
+
"auxillary_file_paths": [
|
57 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-18630702.pt"
|
58 |
+
]
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"metadata": {
|
62 |
+
"stats_format_version": "0.3.0",
|
63 |
+
"mlagents_version": "0.29.0.dev0",
|
64 |
+
"torch_version": "1.13.1+cpu"
|
65 |
+
}
|
66 |
+
}
|