First Push`
Browse files- README.md +35 -0
- SoccerTwos.onnx +3 -0
- SoccerTwos/SoccerTwos-22999458.onnx +3 -0
- SoccerTwos/SoccerTwos-22999458.pt +3 -0
- SoccerTwos/SoccerTwos-23499684.onnx +3 -0
- SoccerTwos/SoccerTwos-23499684.pt +3 -0
- SoccerTwos/SoccerTwos-23999058.onnx +3 -0
- SoccerTwos/SoccerTwos-23999058.pt +3 -0
- SoccerTwos/SoccerTwos-24499574.onnx +3 -0
- SoccerTwos/SoccerTwos-24499574.pt +3 -0
- SoccerTwos/SoccerTwos-24503730.onnx +3 -0
- SoccerTwos/SoccerTwos-24503730.pt +3 -0
- SoccerTwos/checkpoint.pt +3 -0
- SoccerTwos/events.out.tfevents.1712145238.DESKTOP-88HUMTF.7152.0 +3 -0
- SoccerTwos/events.out.tfevents.1712153160.DESKTOP-88HUMTF.25376.0 +3 -0
- config.json +1 -0
- configuration.yaml +84 -0
- run_logs/Player-0.log +0 -0
- run_logs/timers.json +289 -0
- run_logs/training_status.json +66 -0
README.md
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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)
|
15 |
+
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
|
16 |
+
|
17 |
+
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
|
18 |
+
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
|
19 |
+
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
|
20 |
+
- A *longer tutorial* to understand how works ML-Agents:
|
21 |
+
https://huggingface.co/learn/deep-rl-course/unit5/introduction
|
22 |
+
|
23 |
+
### Resume the training
|
24 |
+
```bash
|
25 |
+
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
|
26 |
+
```
|
27 |
+
|
28 |
+
### Watch your Agent play
|
29 |
+
You can watch your agent **playing directly in your browser**
|
30 |
+
|
31 |
+
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
|
32 |
+
2. Step 1: Find your model_id: chanifrusydi/poca-SoccerTwos
|
33 |
+
3. Step 2: Select your *.nn /*.onnx file
|
34 |
+
4. Click on Watch the agent play 👀
|
35 |
+
|
SoccerTwos.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bde3c743bd4ef028256cd3d15806e97826e1f22ec98901c84215b7d376a8d037
|
3 |
+
size 1766876
|
SoccerTwos/SoccerTwos-22999458.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bde3c743bd4ef028256cd3d15806e97826e1f22ec98901c84215b7d376a8d037
|
3 |
+
size 1766876
|
SoccerTwos/SoccerTwos-22999458.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:525dc260a4da5545a5acc7b2efe1bed692158f1eb3a98e31850a0f24c3d45d30
|
3 |
+
size 9480074
|
SoccerTwos/SoccerTwos-23499684.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bde3c743bd4ef028256cd3d15806e97826e1f22ec98901c84215b7d376a8d037
|
3 |
+
size 1766876
|
SoccerTwos/SoccerTwos-23499684.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55c2b37265f3090360ef5fd572b9ab4569c5cf01f21adf5eec58649b871c96ca
|
3 |
+
size 9480074
|
SoccerTwos/SoccerTwos-23999058.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bde3c743bd4ef028256cd3d15806e97826e1f22ec98901c84215b7d376a8d037
|
3 |
+
size 1766876
|
SoccerTwos/SoccerTwos-23999058.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f1aad6163a99acbef2609bbfcf2b9da9537bd040ded9cf15ab8019f90b736db
|
3 |
+
size 9480074
|
SoccerTwos/SoccerTwos-24499574.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bde3c743bd4ef028256cd3d15806e97826e1f22ec98901c84215b7d376a8d037
|
3 |
+
size 1766876
|
SoccerTwos/SoccerTwos-24499574.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5776c92567ebfc73ef59e934a3165d9dafe83b937f4081d009c4a05fc38b4939
|
3 |
+
size 9480074
|
SoccerTwos/SoccerTwos-24503730.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bde3c743bd4ef028256cd3d15806e97826e1f22ec98901c84215b7d376a8d037
|
3 |
+
size 1766876
|
SoccerTwos/SoccerTwos-24503730.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5aeaa99fc203b3d2a7d31350e202f3eccc79d45101704a742008a70add26b2c4
|
3 |
+
size 9480074
|
SoccerTwos/checkpoint.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abeac7879290a478685ce4a89db956e449abfeae825b89655be879aa2a494c52
|
3 |
+
size 9479714
|
SoccerTwos/events.out.tfevents.1712145238.DESKTOP-88HUMTF.7152.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c08214fc635b3708e70dd24c08530e4476f927b14af985d1bab6b1038b53a938
|
3 |
+
size 311764
|
SoccerTwos/events.out.tfevents.1712153160.DESKTOP-88HUMTF.25376.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7366d48c6e11dfcca0b1511f71733b58d468b88a898d89e45740b89f8ef46d90
|
3 |
+
size 17473802
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 44096, "buffer_size": 20480, "learning_rate": 0.003, "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": 500000, "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, "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, "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
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
default_settings: null
|
2 |
+
behaviors:
|
3 |
+
SoccerTwos:
|
4 |
+
trainer_type: poca
|
5 |
+
hyperparameters:
|
6 |
+
batch_size: 44096
|
7 |
+
buffer_size: 20480
|
8 |
+
learning_rate: 0.003
|
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 |
+
checkpoint_interval: 500000
|
17 |
+
network_settings:
|
18 |
+
normalize: false
|
19 |
+
hidden_units: 512
|
20 |
+
num_layers: 2
|
21 |
+
vis_encode_type: simple
|
22 |
+
memory: null
|
23 |
+
goal_conditioning_type: hyper
|
24 |
+
deterministic: false
|
25 |
+
reward_signals:
|
26 |
+
extrinsic:
|
27 |
+
gamma: 0.99
|
28 |
+
strength: 1.0
|
29 |
+
network_settings:
|
30 |
+
normalize: false
|
31 |
+
hidden_units: 128
|
32 |
+
num_layers: 2
|
33 |
+
vis_encode_type: simple
|
34 |
+
memory: null
|
35 |
+
goal_conditioning_type: hyper
|
36 |
+
deterministic: 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
|
44 |
+
self_play:
|
45 |
+
save_steps: 500000
|
46 |
+
team_change: 200000
|
47 |
+
swap_steps: 2000
|
48 |
+
window: 10
|
49 |
+
play_against_latest_model_ratio: 0.5
|
50 |
+
initial_elo: 1200.0
|
51 |
+
behavioral_cloning: null
|
52 |
+
env_settings:
|
53 |
+
env_path: ./training-envs-executables/SoccerTwos.exe
|
54 |
+
env_args: null
|
55 |
+
base_port: 5005
|
56 |
+
num_envs: 1
|
57 |
+
num_areas: 1
|
58 |
+
timeout_wait: 60
|
59 |
+
seed: -1
|
60 |
+
max_lifetime_restarts: 10
|
61 |
+
restarts_rate_limit_n: 1
|
62 |
+
restarts_rate_limit_period_s: 60
|
63 |
+
engine_settings:
|
64 |
+
width: 84
|
65 |
+
height: 84
|
66 |
+
quality_level: 5
|
67 |
+
time_scale: 20
|
68 |
+
target_frame_rate: -1
|
69 |
+
capture_frame_rate: 60
|
70 |
+
no_graphics: false
|
71 |
+
no_graphics_monitor: false
|
72 |
+
environment_parameters: null
|
73 |
+
checkpoint_settings:
|
74 |
+
run_id: SoccerTwos
|
75 |
+
initialize_from: null
|
76 |
+
load_model: false
|
77 |
+
resume: true
|
78 |
+
force: false
|
79 |
+
train_model: false
|
80 |
+
inference: false
|
81 |
+
results_dir: results
|
82 |
+
torch_settings:
|
83 |
+
device: null
|
84 |
+
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 +1,289 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"name": "root",
|
3 |
+
"gauges": {
|
4 |
+
"SoccerTwos.Policy.Entropy.mean": {
|
5 |
+
"value": 3.2957146167755127,
|
6 |
+
"min": 3.2957050800323486,
|
7 |
+
"max": 3.2957236766815186,
|
8 |
+
"count": 2410
|
9 |
+
},
|
10 |
+
"SoccerTwos.Policy.Entropy.sum": {
|
11 |
+
"value": 51676.8046875,
|
12 |
+
"min": 14448.423828125,
|
13 |
+
"max": 160409.109375,
|
14 |
+
"count": 2410
|
15 |
+
},
|
16 |
+
"SoccerTwos.Environment.EpisodeLength.mean": {
|
17 |
+
"value": 934.6,
|
18 |
+
"min": 344.64285714285717,
|
19 |
+
"max": 999.0,
|
20 |
+
"count": 2410
|
21 |
+
},
|
22 |
+
"SoccerTwos.Environment.EpisodeLength.sum": {
|
23 |
+
"value": 18692.0,
|
24 |
+
"min": 11988.0,
|
25 |
+
"max": 29416.0,
|
26 |
+
"count": 2410
|
27 |
+
},
|
28 |
+
"SoccerTwos.Self-play.ELO.mean": {
|
29 |
+
"value": 1179.1023238253106,
|
30 |
+
"min": 1175.3133315039984,
|
31 |
+
"max": 1236.6149935124429,
|
32 |
+
"count": 2193
|
33 |
+
},
|
34 |
+
"SoccerTwos.Self-play.ELO.sum": {
|
35 |
+
"value": 2358.204647650621,
|
36 |
+
"min": 2352.1174047379186,
|
37 |
+
"max": 21999.127537517863,
|
38 |
+
"count": 2193
|
39 |
+
},
|
40 |
+
"SoccerTwos.Step.mean": {
|
41 |
+
"value": 24499574.0,
|
42 |
+
"min": 409819.0,
|
43 |
+
"max": 24499574.0,
|
44 |
+
"count": 2410
|
45 |
+
},
|
46 |
+
"SoccerTwos.Step.sum": {
|
47 |
+
"value": 24499574.0,
|
48 |
+
"min": 409819.0,
|
49 |
+
"max": 24499574.0,
|
50 |
+
"count": 2410
|
51 |
+
},
|
52 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
53 |
+
"value": -0.09331196546554565,
|
54 |
+
"min": -0.09332290291786194,
|
55 |
+
"max": -0.09330271929502487,
|
56 |
+
"count": 2410
|
57 |
+
},
|
58 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
59 |
+
"value": -0.9331196546554565,
|
60 |
+
"min": -2.7061927318573,
|
61 |
+
"max": -0.9330450892448425,
|
62 |
+
"count": 2410
|
63 |
+
},
|
64 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
65 |
+
"value": -0.09329550713300705,
|
66 |
+
"min": -0.09330939501523972,
|
67 |
+
"max": -0.09327684342861176,
|
68 |
+
"count": 2410
|
69 |
+
},
|
70 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
71 |
+
"value": -0.9329550862312317,
|
72 |
+
"min": -2.7055742740631104,
|
73 |
+
"max": -0.9328153133392334,
|
74 |
+
"count": 2410
|
75 |
+
},
|
76 |
+
"SoccerTwos.Environment.CumulativeReward.mean": {
|
77 |
+
"value": 0.0,
|
78 |
+
"min": 0.0,
|
79 |
+
"max": 0.0,
|
80 |
+
"count": 2410
|
81 |
+
},
|
82 |
+
"SoccerTwos.Environment.CumulativeReward.sum": {
|
83 |
+
"value": 0.0,
|
84 |
+
"min": 0.0,
|
85 |
+
"max": 0.0,
|
86 |
+
"count": 2410
|
87 |
+
},
|
88 |
+
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
89 |
+
"value": 0.0,
|
90 |
+
"min": -0.6428571428571429,
|
91 |
+
"max": 0.38829333782196046,
|
92 |
+
"count": 2410
|
93 |
+
},
|
94 |
+
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
95 |
+
"value": 0.0,
|
96 |
+
"min": -10.0,
|
97 |
+
"max": 5.913600027561188,
|
98 |
+
"count": 2410
|
99 |
+
},
|
100 |
+
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
101 |
+
"value": 0.0,
|
102 |
+
"min": -0.6428571428571429,
|
103 |
+
"max": 0.38829333782196046,
|
104 |
+
"count": 2410
|
105 |
+
},
|
106 |
+
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
107 |
+
"value": 0.0,
|
108 |
+
"min": -10.0,
|
109 |
+
"max": 5.913600027561188,
|
110 |
+
"count": 2410
|
111 |
+
},
|
112 |
+
"SoccerTwos.IsTraining.mean": {
|
113 |
+
"value": 1.0,
|
114 |
+
"min": 1.0,
|
115 |
+
"max": 1.0,
|
116 |
+
"count": 2410
|
117 |
+
},
|
118 |
+
"SoccerTwos.IsTraining.sum": {
|
119 |
+
"value": 1.0,
|
120 |
+
"min": 1.0,
|
121 |
+
"max": 1.0,
|
122 |
+
"count": 2410
|
123 |
+
}
|
124 |
+
},
|
125 |
+
"metadata": {
|
126 |
+
"timer_format_version": "0.1.0",
|
127 |
+
"start_time_seconds": "1712153153",
|
128 |
+
"python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
|
129 |
+
"command_line_arguments": "\\\\?\\C:\\ProgramData\\Miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --resume",
|
130 |
+
"mlagents_version": "1.1.0.dev0",
|
131 |
+
"mlagents_envs_version": "1.1.0.dev0",
|
132 |
+
"communication_protocol_version": "1.5.0",
|
133 |
+
"pytorch_version": "2.2.2+cu121",
|
134 |
+
"numpy_version": "1.23.5",
|
135 |
+
"end_time_seconds": "1712183235"
|
136 |
+
},
|
137 |
+
"total": 30080.24656359997,
|
138 |
+
"count": 1,
|
139 |
+
"self": 0.7435149999218993,
|
140 |
+
"children": {
|
141 |
+
"run_training.setup": {
|
142 |
+
"total": 0.100726000033319,
|
143 |
+
"count": 1,
|
144 |
+
"self": 0.100726000033319
|
145 |
+
},
|
146 |
+
"TrainerController.start_learning": {
|
147 |
+
"total": 30079.402322600014,
|
148 |
+
"count": 1,
|
149 |
+
"self": 24.42380688089179,
|
150 |
+
"children": {
|
151 |
+
"TrainerController._reset_env": {
|
152 |
+
"total": 19.894683599704877,
|
153 |
+
"count": 121,
|
154 |
+
"self": 19.894683599704877
|
155 |
+
},
|
156 |
+
"TrainerController.advance": {
|
157 |
+
"total": 30034.979954119364,
|
158 |
+
"count": 1565352,
|
159 |
+
"self": 28.063696226337925,
|
160 |
+
"children": {
|
161 |
+
"env_step": {
|
162 |
+
"total": 25497.624366809032,
|
163 |
+
"count": 1565352,
|
164 |
+
"self": 14555.238549877424,
|
165 |
+
"children": {
|
166 |
+
"SubprocessEnvManager._take_step": {
|
167 |
+
"total": 10924.928921501152,
|
168 |
+
"count": 1565352,
|
169 |
+
"self": 182.60900265473174,
|
170 |
+
"children": {
|
171 |
+
"TorchPolicy.evaluate": {
|
172 |
+
"total": 10742.31991884642,
|
173 |
+
"count": 3106450,
|
174 |
+
"self": 10742.31991884642
|
175 |
+
}
|
176 |
+
}
|
177 |
+
},
|
178 |
+
"workers": {
|
179 |
+
"total": 17.456895430455916,
|
180 |
+
"count": 1565352,
|
181 |
+
"self": 0.0,
|
182 |
+
"children": {
|
183 |
+
"worker_root": {
|
184 |
+
"total": 30034.530063099402,
|
185 |
+
"count": 1565352,
|
186 |
+
"is_parallel": true,
|
187 |
+
"self": 18512.378446593008,
|
188 |
+
"children": {
|
189 |
+
"steps_from_proto": {
|
190 |
+
"total": 0.14015449990984052,
|
191 |
+
"count": 242,
|
192 |
+
"is_parallel": true,
|
193 |
+
"self": 0.0278416009969078,
|
194 |
+
"children": {
|
195 |
+
"_process_rank_one_or_two_observation": {
|
196 |
+
"total": 0.11231289891293272,
|
197 |
+
"count": 968,
|
198 |
+
"is_parallel": true,
|
199 |
+
"self": 0.11231289891293272
|
200 |
+
}
|
201 |
+
}
|
202 |
+
},
|
203 |
+
"UnityEnvironment.step": {
|
204 |
+
"total": 11522.011462006485,
|
205 |
+
"count": 1565352,
|
206 |
+
"is_parallel": true,
|
207 |
+
"self": 584.8113763023284,
|
208 |
+
"children": {
|
209 |
+
"UnityEnvironment._generate_step_input": {
|
210 |
+
"total": 435.0229424237623,
|
211 |
+
"count": 1565352,
|
212 |
+
"is_parallel": true,
|
213 |
+
"self": 435.0229424237623
|
214 |
+
},
|
215 |
+
"communicator.exchange": {
|
216 |
+
"total": 8687.288410618901,
|
217 |
+
"count": 1565352,
|
218 |
+
"is_parallel": true,
|
219 |
+
"self": 8687.288410618901
|
220 |
+
},
|
221 |
+
"steps_from_proto": {
|
222 |
+
"total": 1814.8887326614931,
|
223 |
+
"count": 3130704,
|
224 |
+
"is_parallel": true,
|
225 |
+
"self": 357.6510218011099,
|
226 |
+
"children": {
|
227 |
+
"_process_rank_one_or_two_observation": {
|
228 |
+
"total": 1457.2377108603832,
|
229 |
+
"count": 12522816,
|
230 |
+
"is_parallel": true,
|
231 |
+
"self": 1457.2377108603832
|
232 |
+
}
|
233 |
+
}
|
234 |
+
}
|
235 |
+
}
|
236 |
+
}
|
237 |
+
}
|
238 |
+
}
|
239 |
+
}
|
240 |
+
}
|
241 |
+
}
|
242 |
+
},
|
243 |
+
"trainer_advance": {
|
244 |
+
"total": 4509.291891083994,
|
245 |
+
"count": 1565352,
|
246 |
+
"self": 190.2756298853783,
|
247 |
+
"children": {
|
248 |
+
"process_trajectory": {
|
249 |
+
"total": 2051.1441151972977,
|
250 |
+
"count": 1565352,
|
251 |
+
"self": 2046.685121997085,
|
252 |
+
"children": {
|
253 |
+
"RLTrainer._checkpoint": {
|
254 |
+
"total": 4.458993200212717,
|
255 |
+
"count": 49,
|
256 |
+
"self": 4.458993200212717
|
257 |
+
}
|
258 |
+
}
|
259 |
+
},
|
260 |
+
"_update_policy": {
|
261 |
+
"total": 2267.8721460013185,
|
262 |
+
"count": 1127,
|
263 |
+
"self": 2267.8721460013185
|
264 |
+
}
|
265 |
+
}
|
266 |
+
}
|
267 |
+
}
|
268 |
+
},
|
269 |
+
"trainer_threads": {
|
270 |
+
"total": 1.100008375942707e-06,
|
271 |
+
"count": 1,
|
272 |
+
"self": 1.100008375942707e-06
|
273 |
+
},
|
274 |
+
"TrainerController._save_models": {
|
275 |
+
"total": 0.10387690004426986,
|
276 |
+
"count": 1,
|
277 |
+
"self": 0.0074634000193327665,
|
278 |
+
"children": {
|
279 |
+
"RLTrainer._checkpoint": {
|
280 |
+
"total": 0.0964135000249371,
|
281 |
+
"count": 1,
|
282 |
+
"self": 0.0964135000249371
|
283 |
+
}
|
284 |
+
}
|
285 |
+
}
|
286 |
+
}
|
287 |
+
}
|
288 |
+
}
|
289 |
+
}
|
run_logs/training_status.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"SoccerTwos": {
|
3 |
+
"elo": 1179.1023238253106,
|
4 |
+
"checkpoints": [
|
5 |
+
{
|
6 |
+
"steps": 22999458,
|
7 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-22999458.onnx",
|
8 |
+
"reward": 0.0,
|
9 |
+
"creation_time": 1712181415.9851305,
|
10 |
+
"auxillary_file_paths": [
|
11 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-22999458.pt"
|
12 |
+
]
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"steps": 23499684,
|
16 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-23499684.onnx",
|
17 |
+
"reward": 0.0,
|
18 |
+
"creation_time": 1712182020.1470897,
|
19 |
+
"auxillary_file_paths": [
|
20 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-23499684.pt"
|
21 |
+
]
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"steps": 23999058,
|
25 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-23999058.onnx",
|
26 |
+
"reward": 0.0,
|
27 |
+
"creation_time": 1712182622.3694935,
|
28 |
+
"auxillary_file_paths": [
|
29 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-23999058.pt"
|
30 |
+
]
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"steps": 24499574,
|
34 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-24499574.onnx",
|
35 |
+
"reward": 0.0,
|
36 |
+
"creation_time": 1712183232.6527922,
|
37 |
+
"auxillary_file_paths": [
|
38 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-24499574.pt"
|
39 |
+
]
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"steps": 24503730,
|
43 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-24503730.onnx",
|
44 |
+
"reward": 0.0,
|
45 |
+
"creation_time": 1712183234.9053793,
|
46 |
+
"auxillary_file_paths": [
|
47 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-24503730.pt"
|
48 |
+
]
|
49 |
+
}
|
50 |
+
],
|
51 |
+
"final_checkpoint": {
|
52 |
+
"steps": 24503730,
|
53 |
+
"file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
|
54 |
+
"reward": 0.0,
|
55 |
+
"creation_time": 1712183234.9053793,
|
56 |
+
"auxillary_file_paths": [
|
57 |
+
"results\\SoccerTwos\\SoccerTwos\\SoccerTwos-24503730.pt"
|
58 |
+
]
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"metadata": {
|
62 |
+
"stats_format_version": "0.3.0",
|
63 |
+
"mlagents_version": "1.1.0.dev0",
|
64 |
+
"torch_version": "2.2.2+cu121"
|
65 |
+
}
|
66 |
+
}
|