SoccerTwos 4090
Browse files- README.md +35 -0
- SoccerTwos.onnx +3 -0
- SoccerTwos/SoccerTwos-3569604.pt +3 -0
- SoccerTwos/SoccerTwos-48499022.onnx +3 -0
- SoccerTwos/SoccerTwos-48499022.pt +3 -0
- SoccerTwos/SoccerTwos-48999618.onnx +3 -0
- SoccerTwos/SoccerTwos-48999618.pt +3 -0
- SoccerTwos/SoccerTwos-49499414.onnx +3 -0
- SoccerTwos/SoccerTwos-49499414.pt +3 -0
- SoccerTwos/SoccerTwos-49999654.onnx +3 -0
- SoccerTwos/SoccerTwos-49999654.pt +3 -0
- SoccerTwos/SoccerTwos-50001654.onnx +3 -0
- SoccerTwos/SoccerTwos-50001654.pt +3 -0
- SoccerTwos/checkpoint.pt +3 -0
- SoccerTwos/events.out.tfevents.1694055059.acmai.11593.0 +3 -0
- SoccerTwos/events.out.tfevents.1694057554.acmai.12933.0 +3 -0
- SoccerTwos/events.out.tfevents.1694057684.acmai.13521.0 +3 -0
- SoccerTwos/events.out.tfevents.1694057750.acmai.13925.0 +3 -0
- SoccerTwos/events.out.tfevents.1694057884.acmai.14513.0 +3 -0
- SoccerTwos/events.out.tfevents.1694058101.acmai.15337.0 +3 -0
- SoccerTwos/events.out.tfevents.1694058176.acmai.15765.0 +3 -0
- SoccerTwos/events.out.tfevents.1694058239.acmai.16160.0 +3 -0
- SoccerTwos/events.out.tfevents.1694058414.acmai.16871.0 +3 -0
- SoccerTwos/events.out.tfevents.1694066726.acmai.40014.0 +3 -0
- config.json +1 -0
- configuration.yaml +82 -0
- run_logs/Player-0.log +0 -0
- run_logs/timers.json +424 -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: ShreyasM/SoccerTwos4090
|
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:ed07e0669f4c949cc28663910f90454eb0711c3c992f9f40db84e7a1203210bb
|
3 |
+
size 237841286
|
SoccerTwos/SoccerTwos-3569604.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5b7eb461e17e7fe0da14458a6236ff970fef6cf69773ec4f86d2e921566cd3f
|
3 |
+
size 562392221
|
SoccerTwos/SoccerTwos-48499022.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed07e0669f4c949cc28663910f90454eb0711c3c992f9f40db84e7a1203210bb
|
3 |
+
size 237841286
|
SoccerTwos/SoccerTwos-48499022.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33ca5bcd8efd2fed11e313717524c2d11c240c007d83f6b21973bced986b573a
|
3 |
+
size 1687152017
|
SoccerTwos/SoccerTwos-48999618.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed07e0669f4c949cc28663910f90454eb0711c3c992f9f40db84e7a1203210bb
|
3 |
+
size 237841286
|
SoccerTwos/SoccerTwos-48999618.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da703b0dd0cb805f8cd024985e84f946f0715464ab244421d2efd7936b5876af
|
3 |
+
size 1687152017
|
SoccerTwos/SoccerTwos-49499414.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed07e0669f4c949cc28663910f90454eb0711c3c992f9f40db84e7a1203210bb
|
3 |
+
size 237841286
|
SoccerTwos/SoccerTwos-49499414.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9e16b77632b5fca122bf15211a265a9f41ed85f3277f9e58df95c748cd21038
|
3 |
+
size 1687152017
|
SoccerTwos/SoccerTwos-49999654.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed07e0669f4c949cc28663910f90454eb0711c3c992f9f40db84e7a1203210bb
|
3 |
+
size 237841286
|
SoccerTwos/SoccerTwos-49999654.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:109cbf3199405f4f6cfe10ac54f9bbbf597d7da2acd0d0359fe9b877e7ae13ab
|
3 |
+
size 1687152017
|
SoccerTwos/SoccerTwos-50001654.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed07e0669f4c949cc28663910f90454eb0711c3c992f9f40db84e7a1203210bb
|
3 |
+
size 237841286
|
SoccerTwos/SoccerTwos-50001654.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a684df4b8a4608f2cd90d2f1128c1ca230f28669878896ca1f36ac4849b8da8
|
3 |
+
size 1687152017
|
SoccerTwos/checkpoint.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a684df4b8a4608f2cd90d2f1128c1ca230f28669878896ca1f36ac4849b8da8
|
3 |
+
size 1687152017
|
SoccerTwos/events.out.tfevents.1694055059.acmai.11593.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20ecad4f9a3ee9121e926c54bd42f95137a4d056967ea1f4d1bc7b9c5410212c
|
3 |
+
size 2759165
|
SoccerTwos/events.out.tfevents.1694057554.acmai.12933.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cbb246cc3ed4e8ced9c87a803291192553b7c4f83b0d3cc5b3663bbcfb2f19f
|
3 |
+
size 64798
|
SoccerTwos/events.out.tfevents.1694057684.acmai.13521.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a19bb6a94f83f27bfb872f0aa11bcbf0b7e76483166d63b03167a2a7d4a5050
|
3 |
+
size 27601
|
SoccerTwos/events.out.tfevents.1694057750.acmai.13925.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9d9ed2eff32ff4b106ce3fa957ea3818738f77b3ab3bea696ef5e6e2e178a54
|
3 |
+
size 68923
|
SoccerTwos/events.out.tfevents.1694057884.acmai.14513.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd4c35a36bb0b09ed447f66e95d884687653ee5459f34097327a60df73f90838
|
3 |
+
size 146915
|
SoccerTwos/events.out.tfevents.1694058101.acmai.15337.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4d739d318095550d36fa875badf5dc9e429a559ab34ae291e230a18a3f43e17
|
3 |
+
size 21160
|
SoccerTwos/events.out.tfevents.1694058176.acmai.15765.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0acad93a5ec48992abbbdf15d36e6017abbe70e40c994b85934401be42f7fd3
|
3 |
+
size 21432
|
SoccerTwos/events.out.tfevents.1694058239.acmai.16160.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a7c99fb2e9e760b3ff5ab2b26bc3300cf8172bb4850355d74387869e469614a
|
3 |
+
size 78045
|
SoccerTwos/events.out.tfevents.1694058414.acmai.16871.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75c1f25bb5be815accf3463b879525b842df3036583c38238a667a794656d3a6
|
3 |
+
size 5775947
|
SoccerTwos/events.out.tfevents.1694066726.acmai.40014.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a105100a439f75093650e2cf646b4607d70251762410a1a047332c25753857d
|
3 |
+
size 24395975
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 8192, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 2048, "num_layers": 15, "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": "./trained-envs-executables/SoccerTwos/SoccerTwos.x86_64", "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
|
configuration.yaml
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
default_settings: null
|
2 |
+
behaviors:
|
3 |
+
SoccerTwos:
|
4 |
+
trainer_type: poca
|
5 |
+
hyperparameters:
|
6 |
+
batch_size: 8192
|
7 |
+
buffer_size: 20480
|
8 |
+
learning_rate: 0.0003
|
9 |
+
beta: 0.005
|
10 |
+
epsilon: 0.2
|
11 |
+
lambd: 0.95
|
12 |
+
num_epoch: 5
|
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: 2048
|
20 |
+
num_layers: 15
|
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: 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
|
51 |
+
behavioral_cloning: null
|
52 |
+
env_settings:
|
53 |
+
env_path: ./trained-envs-executables/SoccerTwos/SoccerTwos.x86_64
|
54 |
+
env_args: null
|
55 |
+
base_port: 5005
|
56 |
+
num_envs: 1
|
57 |
+
num_areas: 1
|
58 |
+
seed: -1
|
59 |
+
max_lifetime_restarts: 10
|
60 |
+
restarts_rate_limit_n: 1
|
61 |
+
restarts_rate_limit_period_s: 60
|
62 |
+
engine_settings:
|
63 |
+
width: 84
|
64 |
+
height: 84
|
65 |
+
quality_level: 5
|
66 |
+
time_scale: 20
|
67 |
+
target_frame_rate: -1
|
68 |
+
capture_frame_rate: 60
|
69 |
+
no_graphics: true
|
70 |
+
environment_parameters: null
|
71 |
+
checkpoint_settings:
|
72 |
+
run_id: SoccerTwos
|
73 |
+
initialize_from: null
|
74 |
+
load_model: false
|
75 |
+
resume: true
|
76 |
+
force: false
|
77 |
+
train_model: false
|
78 |
+
inference: false
|
79 |
+
results_dir: results
|
80 |
+
torch_settings:
|
81 |
+
device: null
|
82 |
+
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 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"name": "root",
|
3 |
+
"gauges": {
|
4 |
+
"SoccerTwos.Policy.Entropy.mean": {
|
5 |
+
"value": -3.576278402306343e-07,
|
6 |
+
"min": -3.576278402306343e-07,
|
7 |
+
"max": 3.2945072650909424,
|
8 |
+
"count": 3825
|
9 |
+
},
|
10 |
+
"SoccerTwos.Policy.Entropy.sum": {
|
11 |
+
"value": -0.00781631376594305,
|
12 |
+
"min": -0.019557951018214226,
|
13 |
+
"max": 167398.328125,
|
14 |
+
"count": 3825
|
15 |
+
},
|
16 |
+
"SoccerTwos.Environment.EpisodeLength.mean": {
|
17 |
+
"value": 720.1428571428571,
|
18 |
+
"min": 285.06666666666666,
|
19 |
+
"max": 999.0,
|
20 |
+
"count": 3825
|
21 |
+
},
|
22 |
+
"SoccerTwos.Environment.EpisodeLength.sum": {
|
23 |
+
"value": 20164.0,
|
24 |
+
"min": 3660.0,
|
25 |
+
"max": 28808.0,
|
26 |
+
"count": 3825
|
27 |
+
},
|
28 |
+
"SoccerTwos.Self-play.ELO.mean": {
|
29 |
+
"value": 1569.9423849064597,
|
30 |
+
"min": 1530.1366432078805,
|
31 |
+
"max": 1635.3633316190458,
|
32 |
+
"count": 3074
|
33 |
+
},
|
34 |
+
"SoccerTwos.Self-play.ELO.sum": {
|
35 |
+
"value": 6279.769539625839,
|
36 |
+
"min": 3060.273286415761,
|
37 |
+
"max": 27767.161065008182,
|
38 |
+
"count": 3074
|
39 |
+
},
|
40 |
+
"SoccerTwos.Step.mean": {
|
41 |
+
"value": 49999654.0,
|
42 |
+
"min": 11759873.0,
|
43 |
+
"max": 49999654.0,
|
44 |
+
"count": 3825
|
45 |
+
},
|
46 |
+
"SoccerTwos.Step.sum": {
|
47 |
+
"value": 49999654.0,
|
48 |
+
"min": 11759873.0,
|
49 |
+
"max": 49999654.0,
|
50 |
+
"count": 3825
|
51 |
+
},
|
52 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
53 |
+
"value": -0.009638502262532711,
|
54 |
+
"min": -0.026710689067840576,
|
55 |
+
"max": 0.011438295245170593,
|
56 |
+
"count": 3825
|
57 |
+
},
|
58 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
59 |
+
"value": -0.1349390298128128,
|
60 |
+
"min": -0.47578129172325134,
|
61 |
+
"max": 0.2820509672164917,
|
62 |
+
"count": 3825
|
63 |
+
},
|
64 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
65 |
+
"value": -0.009638502262532711,
|
66 |
+
"min": -0.026710689067840576,
|
67 |
+
"max": 0.011438295245170593,
|
68 |
+
"count": 3825
|
69 |
+
},
|
70 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
71 |
+
"value": -0.1349390298128128,
|
72 |
+
"min": -0.47578129172325134,
|
73 |
+
"max": 0.2820509672164917,
|
74 |
+
"count": 3825
|
75 |
+
},
|
76 |
+
"SoccerTwos.Environment.CumulativeReward.mean": {
|
77 |
+
"value": 0.0,
|
78 |
+
"min": 0.0,
|
79 |
+
"max": 0.0,
|
80 |
+
"count": 3825
|
81 |
+
},
|
82 |
+
"SoccerTwos.Environment.CumulativeReward.sum": {
|
83 |
+
"value": 0.0,
|
84 |
+
"min": 0.0,
|
85 |
+
"max": 0.0,
|
86 |
+
"count": 3825
|
87 |
+
},
|
88 |
+
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
89 |
+
"value": -0.002171431268964495,
|
90 |
+
"min": -0.625,
|
91 |
+
"max": 0.45912940361920523,
|
92 |
+
"count": 3825
|
93 |
+
},
|
94 |
+
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
95 |
+
"value": -0.03040003776550293,
|
96 |
+
"min": -12.0,
|
97 |
+
"max": 9.62279999256134,
|
98 |
+
"count": 3825
|
99 |
+
},
|
100 |
+
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
101 |
+
"value": -0.002171431268964495,
|
102 |
+
"min": -0.625,
|
103 |
+
"max": 0.45912940361920523,
|
104 |
+
"count": 3825
|
105 |
+
},
|
106 |
+
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
107 |
+
"value": -0.03040003776550293,
|
108 |
+
"min": -12.0,
|
109 |
+
"max": 9.62279999256134,
|
110 |
+
"count": 3825
|
111 |
+
},
|
112 |
+
"SoccerTwos.IsTraining.mean": {
|
113 |
+
"value": 1.0,
|
114 |
+
"min": 1.0,
|
115 |
+
"max": 1.0,
|
116 |
+
"count": 3825
|
117 |
+
},
|
118 |
+
"SoccerTwos.IsTraining.sum": {
|
119 |
+
"value": 1.0,
|
120 |
+
"min": 1.0,
|
121 |
+
"max": 1.0,
|
122 |
+
"count": 3825
|
123 |
+
},
|
124 |
+
"SoccerTwos.Losses.PolicyLoss.mean": {
|
125 |
+
"value": 0.005191320995800197,
|
126 |
+
"min": 0.0025595865241484716,
|
127 |
+
"max": 0.0512155355347204,
|
128 |
+
"count": 1754
|
129 |
+
},
|
130 |
+
"SoccerTwos.Losses.PolicyLoss.sum": {
|
131 |
+
"value": 0.005191320995800197,
|
132 |
+
"min": 0.0025595865241484716,
|
133 |
+
"max": 0.0512155355347204,
|
134 |
+
"count": 1754
|
135 |
+
},
|
136 |
+
"SoccerTwos.Losses.ValueLoss.mean": {
|
137 |
+
"value": 0.004174860217608512,
|
138 |
+
"min": 1.987874747866325e-08,
|
139 |
+
"max": 0.009012238495051861,
|
140 |
+
"count": 1754
|
141 |
+
},
|
142 |
+
"SoccerTwos.Losses.ValueLoss.sum": {
|
143 |
+
"value": 0.004174860217608512,
|
144 |
+
"min": 1.987874747866325e-08,
|
145 |
+
"max": 0.009012238495051861,
|
146 |
+
"count": 1754
|
147 |
+
},
|
148 |
+
"SoccerTwos.Losses.BaselineLoss.mean": {
|
149 |
+
"value": 0.004174860217608512,
|
150 |
+
"min": 1.987874747866325e-08,
|
151 |
+
"max": 0.009012238495051861,
|
152 |
+
"count": 1754
|
153 |
+
},
|
154 |
+
"SoccerTwos.Losses.BaselineLoss.sum": {
|
155 |
+
"value": 0.004174860217608512,
|
156 |
+
"min": 1.987874747866325e-08,
|
157 |
+
"max": 0.009012238495051861,
|
158 |
+
"count": 1754
|
159 |
+
},
|
160 |
+
"SoccerTwos.Policy.LearningRate.mean": {
|
161 |
+
"value": 0.0003,
|
162 |
+
"min": 0.0003,
|
163 |
+
"max": 0.0003,
|
164 |
+
"count": 1754
|
165 |
+
},
|
166 |
+
"SoccerTwos.Policy.LearningRate.sum": {
|
167 |
+
"value": 0.0003,
|
168 |
+
"min": 0.0003,
|
169 |
+
"max": 0.0003,
|
170 |
+
"count": 1754
|
171 |
+
},
|
172 |
+
"SoccerTwos.Policy.Epsilon.mean": {
|
173 |
+
"value": 0.2,
|
174 |
+
"min": 0.2,
|
175 |
+
"max": 0.2,
|
176 |
+
"count": 1754
|
177 |
+
},
|
178 |
+
"SoccerTwos.Policy.Epsilon.sum": {
|
179 |
+
"value": 0.2,
|
180 |
+
"min": 0.2,
|
181 |
+
"max": 0.2,
|
182 |
+
"count": 1754
|
183 |
+
},
|
184 |
+
"SoccerTwos.Policy.Beta.mean": {
|
185 |
+
"value": 0.004999999999999999,
|
186 |
+
"min": 0.004999999999999999,
|
187 |
+
"max": 0.004999999999999999,
|
188 |
+
"count": 1754
|
189 |
+
},
|
190 |
+
"SoccerTwos.Policy.Beta.sum": {
|
191 |
+
"value": 0.004999999999999999,
|
192 |
+
"min": 0.004999999999999999,
|
193 |
+
"max": 0.004999999999999999,
|
194 |
+
"count": 1754
|
195 |
+
}
|
196 |
+
},
|
197 |
+
"metadata": {
|
198 |
+
"timer_format_version": "0.1.0",
|
199 |
+
"start_time_seconds": "1694066726",
|
200 |
+
"python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]",
|
201 |
+
"command_line_arguments": "/home/acm/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./trained-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
|
202 |
+
"mlagents_version": "0.31.0.dev0",
|
203 |
+
"mlagents_envs_version": "0.31.0.dev0",
|
204 |
+
"communication_protocol_version": "1.5.0",
|
205 |
+
"pytorch_version": "1.11.0+cu113",
|
206 |
+
"numpy_version": "1.21.2",
|
207 |
+
"end_time_seconds": "1694104736"
|
208 |
+
},
|
209 |
+
"total": 38009.418713622,
|
210 |
+
"count": 1,
|
211 |
+
"self": 0.16675795900664525,
|
212 |
+
"children": {
|
213 |
+
"run_training.setup": {
|
214 |
+
"total": 0.0044328529984341,
|
215 |
+
"count": 1,
|
216 |
+
"self": 0.0044328529984341
|
217 |
+
},
|
218 |
+
"TrainerController.start_learning": {
|
219 |
+
"total": 38009.247522809994,
|
220 |
+
"count": 1,
|
221 |
+
"self": 16.779527878439694,
|
222 |
+
"children": {
|
223 |
+
"TrainerController._reset_env": {
|
224 |
+
"total": 12.369896524967771,
|
225 |
+
"count": 192,
|
226 |
+
"self": 12.369896524967771
|
227 |
+
},
|
228 |
+
"TrainerController.advance": {
|
229 |
+
"total": 37977.201706746586,
|
230 |
+
"count": 2497504,
|
231 |
+
"self": 17.63627195636218,
|
232 |
+
"children": {
|
233 |
+
"env_step": {
|
234 |
+
"total": 25689.303988712014,
|
235 |
+
"count": 2497504,
|
236 |
+
"self": 20316.80456168284,
|
237 |
+
"children": {
|
238 |
+
"SubprocessEnvManager._take_step": {
|
239 |
+
"total": 5361.335743209242,
|
240 |
+
"count": 2497504,
|
241 |
+
"self": 139.39434876448286,
|
242 |
+
"children": {
|
243 |
+
"TorchPolicy.evaluate": {
|
244 |
+
"total": 5221.941394444759,
|
245 |
+
"count": 4954172,
|
246 |
+
"self": 5221.941394444759
|
247 |
+
}
|
248 |
+
}
|
249 |
+
},
|
250 |
+
"workers": {
|
251 |
+
"total": 11.163683819933794,
|
252 |
+
"count": 2497504,
|
253 |
+
"self": 0.0,
|
254 |
+
"children": {
|
255 |
+
"worker_root": {
|
256 |
+
"total": 37940.311905019604,
|
257 |
+
"count": 2497504,
|
258 |
+
"is_parallel": true,
|
259 |
+
"self": 20382.960668171065,
|
260 |
+
"children": {
|
261 |
+
"run_training.setup": {
|
262 |
+
"total": 0.0,
|
263 |
+
"count": 0,
|
264 |
+
"is_parallel": true,
|
265 |
+
"self": 0.0,
|
266 |
+
"children": {
|
267 |
+
"steps_from_proto": {
|
268 |
+
"total": 0.0018097739994118456,
|
269 |
+
"count": 2,
|
270 |
+
"is_parallel": true,
|
271 |
+
"self": 0.0003727360090124421,
|
272 |
+
"children": {
|
273 |
+
"_process_rank_one_or_two_observation": {
|
274 |
+
"total": 0.0014370379903994035,
|
275 |
+
"count": 8,
|
276 |
+
"is_parallel": true,
|
277 |
+
"self": 0.0014370379903994035
|
278 |
+
}
|
279 |
+
}
|
280 |
+
},
|
281 |
+
"UnityEnvironment.step": {
|
282 |
+
"total": 0.013925006998761091,
|
283 |
+
"count": 1,
|
284 |
+
"is_parallel": true,
|
285 |
+
"self": 0.0004372239964141045,
|
286 |
+
"children": {
|
287 |
+
"UnityEnvironment._generate_step_input": {
|
288 |
+
"total": 0.0003484500011836644,
|
289 |
+
"count": 1,
|
290 |
+
"is_parallel": true,
|
291 |
+
"self": 0.0003484500011836644
|
292 |
+
},
|
293 |
+
"communicator.exchange": {
|
294 |
+
"total": 0.011721148999640718,
|
295 |
+
"count": 1,
|
296 |
+
"is_parallel": true,
|
297 |
+
"self": 0.011721148999640718
|
298 |
+
},
|
299 |
+
"steps_from_proto": {
|
300 |
+
"total": 0.0014181840015226044,
|
301 |
+
"count": 2,
|
302 |
+
"is_parallel": true,
|
303 |
+
"self": 0.00026026300474768505,
|
304 |
+
"children": {
|
305 |
+
"_process_rank_one_or_two_observation": {
|
306 |
+
"total": 0.0011579209967749193,
|
307 |
+
"count": 8,
|
308 |
+
"is_parallel": true,
|
309 |
+
"self": 0.0011579209967749193
|
310 |
+
}
|
311 |
+
}
|
312 |
+
}
|
313 |
+
}
|
314 |
+
}
|
315 |
+
}
|
316 |
+
},
|
317 |
+
"steps_from_proto": {
|
318 |
+
"total": 0.26497412007302046,
|
319 |
+
"count": 382,
|
320 |
+
"is_parallel": true,
|
321 |
+
"self": 0.04817248907056637,
|
322 |
+
"children": {
|
323 |
+
"_process_rank_one_or_two_observation": {
|
324 |
+
"total": 0.2168016310024541,
|
325 |
+
"count": 1528,
|
326 |
+
"is_parallel": true,
|
327 |
+
"self": 0.2168016310024541
|
328 |
+
}
|
329 |
+
}
|
330 |
+
},
|
331 |
+
"UnityEnvironment.step": {
|
332 |
+
"total": 17557.086262728466,
|
333 |
+
"count": 2497503,
|
334 |
+
"is_parallel": true,
|
335 |
+
"self": 1040.7441306267792,
|
336 |
+
"children": {
|
337 |
+
"UnityEnvironment._generate_step_input": {
|
338 |
+
"total": 696.1562557399302,
|
339 |
+
"count": 2497503,
|
340 |
+
"is_parallel": true,
|
341 |
+
"self": 696.1562557399302
|
342 |
+
},
|
343 |
+
"communicator.exchange": {
|
344 |
+
"total": 12537.580525180903,
|
345 |
+
"count": 2497503,
|
346 |
+
"is_parallel": true,
|
347 |
+
"self": 12537.580525180903
|
348 |
+
},
|
349 |
+
"steps_from_proto": {
|
350 |
+
"total": 3282.605351180853,
|
351 |
+
"count": 4995006,
|
352 |
+
"is_parallel": true,
|
353 |
+
"self": 520.684407304172,
|
354 |
+
"children": {
|
355 |
+
"_process_rank_one_or_two_observation": {
|
356 |
+
"total": 2761.920943876681,
|
357 |
+
"count": 19980024,
|
358 |
+
"is_parallel": true,
|
359 |
+
"self": 2761.920943876681
|
360 |
+
}
|
361 |
+
}
|
362 |
+
}
|
363 |
+
}
|
364 |
+
}
|
365 |
+
}
|
366 |
+
}
|
367 |
+
}
|
368 |
+
}
|
369 |
+
}
|
370 |
+
},
|
371 |
+
"trainer_advance": {
|
372 |
+
"total": 12270.26144607821,
|
373 |
+
"count": 2497504,
|
374 |
+
"self": 223.05618517052426,
|
375 |
+
"children": {
|
376 |
+
"process_trajectory": {
|
377 |
+
"total": 1873.0487656927762,
|
378 |
+
"count": 2497504,
|
379 |
+
"self": 1659.739481237826,
|
380 |
+
"children": {
|
381 |
+
"RLTrainer._checkpoint": {
|
382 |
+
"total": 213.3092844549501,
|
383 |
+
"count": 77,
|
384 |
+
"self": 213.3092844549501
|
385 |
+
}
|
386 |
+
}
|
387 |
+
},
|
388 |
+
"_update_policy": {
|
389 |
+
"total": 10174.15649521491,
|
390 |
+
"count": 1754,
|
391 |
+
"self": 4030.5775346320224,
|
392 |
+
"children": {
|
393 |
+
"TorchPOCAOptimizer.update": {
|
394 |
+
"total": 6143.578960582887,
|
395 |
+
"count": 17540,
|
396 |
+
"self": 6143.578960582887
|
397 |
+
}
|
398 |
+
}
|
399 |
+
}
|
400 |
+
}
|
401 |
+
}
|
402 |
+
}
|
403 |
+
},
|
404 |
+
"trainer_threads": {
|
405 |
+
"total": 4.00003045797348e-07,
|
406 |
+
"count": 1,
|
407 |
+
"self": 4.00003045797348e-07
|
408 |
+
},
|
409 |
+
"TrainerController._save_models": {
|
410 |
+
"total": 2.896391259993834,
|
411 |
+
"count": 1,
|
412 |
+
"self": 0.13090770099370275,
|
413 |
+
"children": {
|
414 |
+
"RLTrainer._checkpoint": {
|
415 |
+
"total": 2.765483559000131,
|
416 |
+
"count": 1,
|
417 |
+
"self": 2.765483559000131
|
418 |
+
}
|
419 |
+
}
|
420 |
+
}
|
421 |
+
}
|
422 |
+
}
|
423 |
+
}
|
424 |
+
}
|
run_logs/training_status.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"SoccerTwos": {
|
3 |
+
"checkpoints": [
|
4 |
+
{
|
5 |
+
"steps": 48499022,
|
6 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499022.onnx",
|
7 |
+
"reward": 0.0,
|
8 |
+
"creation_time": 1694103240.1409404,
|
9 |
+
"auxillary_file_paths": [
|
10 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-48499022.pt"
|
11 |
+
]
|
12 |
+
},
|
13 |
+
{
|
14 |
+
"steps": 48999618,
|
15 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999618.onnx",
|
16 |
+
"reward": 0.0,
|
17 |
+
"creation_time": 1694103740.068868,
|
18 |
+
"auxillary_file_paths": [
|
19 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-48999618.pt"
|
20 |
+
]
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"steps": 49499414,
|
24 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499414.onnx",
|
25 |
+
"reward": 0.0,
|
26 |
+
"creation_time": 1694104228.4071314,
|
27 |
+
"auxillary_file_paths": [
|
28 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-49499414.pt"
|
29 |
+
]
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"steps": 49999654,
|
33 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999654.onnx",
|
34 |
+
"reward": 0.0,
|
35 |
+
"creation_time": 1694104732.9276788,
|
36 |
+
"auxillary_file_paths": [
|
37 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-49999654.pt"
|
38 |
+
]
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"steps": 50001654,
|
42 |
+
"file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50001654.onnx",
|
43 |
+
"reward": 0.0,
|
44 |
+
"creation_time": 1694104735.7710335,
|
45 |
+
"auxillary_file_paths": [
|
46 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-50001654.pt"
|
47 |
+
]
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"elo": 1569.9423849064597,
|
51 |
+
"final_checkpoint": {
|
52 |
+
"steps": 50001654,
|
53 |
+
"file_path": "results/SoccerTwos/SoccerTwos.onnx",
|
54 |
+
"reward": 0.0,
|
55 |
+
"creation_time": 1694104735.7710335,
|
56 |
+
"auxillary_file_paths": [
|
57 |
+
"results/SoccerTwos/SoccerTwos/SoccerTwos-50001654.pt"
|
58 |
+
]
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"metadata": {
|
62 |
+
"stats_format_version": "0.3.0",
|
63 |
+
"mlagents_version": "0.31.0.dev0",
|
64 |
+
"torch_version": "1.11.0+cu113"
|
65 |
+
}
|
66 |
+
}
|