hangzhou-mahjong
Hangzhou Mahjong training and evaluation framework with public-information Transformers, paired branch reinforcement learning, and the r2600 checkpoint.
Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.
This is 1 of 55 launches in reinforcement learning frameworks — see how it stacks up on momentum and crowding →
1105 other launches read as similar to this one →
Details
- External ID
- 1413297121
- Source
- GITHUB
- Company
- —
- Product
- hangzhou-mahjong
- Website domain
- github.com
- Launched
- Oct. 10, 2026
- Cohort
- —
- Upvotes
- 100
- Upvotes percentile
- 0.84
- Tags
- —
Enrichment
- Niche
- reinforcement learning frameworks
- Vertical
- Media & entertainment
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- reinforcement learning framework for hangzhou mahjong
- Manually corrected
- False
Could you build this?
No This is a complex competitive reinforcement learning research framework featuring custom Transformer architectures, imperfect-information game theory, and distributed RL training pipelines.
What it would actually take: Requires PyTorch/JAX, distributed reinforcement learning algorithms tailored to partial-observability games (e.g., paired branch RL, regret minimization), high-performance C++ game environment simulators, and massive GPU cluster training compute to converge to superhuman play.
Competitors
Other products that read as similar to this one — 1105 launches clear the similarity bar, closest 8 shown.
Attention rank: #178 of 1106 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 344 days after the earliest competitor.
- Tropical-Reinforcement-Learning · github · 2026-10-06 · 12 upvotes · similarity 0.59
- awesome-post-training-RL · github · 2026-09-11 · 11 upvotes · similarity 0.59
- score-centering · github · 2026-09-14 · 11 upvotes · similarity 0.56
- CUA-Sandbox-Efficient-Environments-for-Computer-Use-Reinforcement-Learning · github · 2026-09-26 · 9 upvotes · similarity 0.54
- queen · github · 2026-10-02 · 21 upvotes · similarity 0.53
- JevAny · github · 2026-09-22 · 17 upvotes · similarity 0.53
- EasyPPO · github · 2026-09-29 · 15 upvotes · similarity 0.53
- MorphMove · ph · 2026-09-10 · 2 upvotes · similarity 0.53
Other launches for this product
- No other launches for this product.