Downloads · 30 days
0
alphachu-v1
alphachu-volleyball/alphachu-v1
alphachu-v1 is a reinforcement learning model from alphachu-volleyball. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for stable-baselines3. The card lists the license as mit.
First deployed model for world-tournament.
Access
Public
Updated Apr 9, 2026
Repo size
23.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp427.7 MB · 100%
At a glance
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- License
- mit
- Access
- Public
- Created
- Apr 9, 2026
- Updated
- Apr 9, 2026
- SHA
- 60fc707d
Model card
From the Hugging Face model README
alphachu-v1
First deployed model for world-tournament.
Source
- Experiment: 016_continue_015_extend, checkpoint_000015 (step ~111M)
- W&B run: https://wandb.ai/ootzk/alphachu-volleyball/runs/tv00fzku
- Training: curriculum crossplay, pre-duckll:5 unlock
Model config
| Field | Value |
|---|---|
| Side | player_1 |
| Action simplified | true |
| Obs simplified | false |
| Obs normalized | true |
| Size | 29.7 KB (ONNX) |
Win rates at checkpoint_000015 (Iter 15, 100 games each)
| Opponent | Win | Loss | Win rate |
|---|---|---|---|
| random | 100 | 0 | 100% |
| stone | 100 | 0 | 100% |
| builtin | 100 | 0 | 100% |
| duckll:0 | 100 | 0 | 100% |
| duckll:1 | 100 | 0 | 100% |
| duckll:2 | 94 | 6 | 94% |
| duckll:3 | 90 | 10 | 90% |
| duckll:7 | 85 | 15 | 85% |
Average pool win rate: 96.1%
Gameplay videos (5-point matches)
vs human
<video src="https://huggingface.co/alphachu-volleyball/alphachu-v1/resolve/main/videos/vs_human.mp4" controls></video>
vs duckll:7
<video src="https://huggingface.co/alphachu-volleyball/alphachu-v1/resolve/main/videos/vs_duckll_7.mp4" controls></video>
vs duckll:3
<video src="https://huggingface.co/alphachu-volleyball/alphachu-v1/resolve/main/videos/vs_duckll_3.mp4" controls></video>
vs duckll:2
<video src="https://huggingface.co/alphachu-volleyball/alphachu-v1/resolve/main/videos/vs_duckll_2.mp4" controls></video>
vs duckll:1
<video src="https://huggingface.co/alphachu-volleyball/alphachu-v1/resolve/main/videos/vs_duckll_1.mp4" controls></video>
vs duckll:0
<video src="https://huggingface.co/alphachu-volleyball/alphachu-v1/resolve/main/videos/vs_duckll_0.mp4" controls></video>
vs builtin
<video src="https://huggingface.co/alphachu-volleyball/alphachu-v1/resolve/main/videos/vs_builtin.mp4" controls></video>
vs stone
<video src="https://huggingface.co/alphachu-volleyball/alphachu-v1/resolve/main/videos/vs_stone.mp4" controls></video>
vs random
<video src="https://huggingface.co/alphachu-volleyball/alphachu-v1/resolve/main/videos/vs_random.mp4" controls></video>
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- License
- mit
- Created
- Apr 9, 2026
- Updated
- Apr 9, 2026