TanyaoDojo — Mahjong AI checkpoints

JAX/Flax checkpoints from TanyaoDojo, a from-scratch mahjong AI stack (vectorized env + behavior cloning + self-play RL). Every number below comes from the same duplicate 1v3 protocol: the challenger plays all four seats over identical walls against three copies of a strong open-source baseline (Mortal v4), seed_key=20260711, seeds from 10000, placement points [90, 45, 0, -135].

avg_pt is the challenger's mean placement points relative to the baseline; 0 would mean parity. Higher is better.

The headline checkpoint has a 100k-game milestone measurement (-4.66 +/- 0.535, 16.0M decisions, zero fallbacks) — not a small-sample estimate.

Checkpoints

File	Arch	Obs	Training	avg_pt vs baseline
bc_v2_g186.pkl	256ch x 10blk (12.4M)	v2 (34x36 + 32)	BC on 10y logs + LR-1e-4 refine	-4.66 +/- 0.535 (100k games)
bc_lean_g402.pkl	256ch x 10blk (12.4M)	lean (34x20 + 26)	BC on 14y logs + LR-1e-4 refine	-5.07 +/- 1.54 (12k games)
bc_lean_w192_ep2.pkl	192ch x 8blk (5.3M)	lean	BC on 6y logs, 2 epochs	-8.87 +/- 2.70 (4k games)
rl_oracle_800m.pkl	256ch x 10blk	lean (actor)	oracle-critic PPO league, 0.8B steps	-8.38 +/- 2.65 (4k games) — negative result

The last row is published deliberately: an asymmetric actor-critic whose critic sees all four hands fit the value function ~100x better (v_loss 0.102 -> 0.001) yet lost 3.2pt of external strength. It is one of four consecutive negative RL results in this project; the bottleneck appears to sit between the advantage signal and the policy update, not in value estimation.

Format

Plain pickle of a Flax parameter pytree for LeanACNet(channels, blocks) (see jax_rl/net_lean.py in the repo). Load and run:

import pickle, jax
from net_lean import LeanACNet          # from the TanyaoDojo repo
from obs_v2 import observe_v2           # or obs_lean.observe_lean

params = pickle.load(open("bc_v2_g186.pkl", "rb"))
net = LeanACNet(channels=256, blocks=10)
logits, value = net.apply(params, observe_v2(state))   # state: Mahjax red_mahjong State

Observation must match the checkpoint: bc_v2_* needs obs_v2 (36 planes), everything else needs obs_lean (20 planes). Planes are stored as uint8 * scale in datasets (scale 24 for v2, 4 for lean) and divided back at train/eval time.

Evaluation harness: jax_rl/mjai_bot/run_eval.py in the repo (--obs v2 for the v2 checkpoint).

Training data — not distributed

These models were trained on Tenhou houou-level game logs. Neither the logs nor the derived datasets are redistributed here, per Tenhou's terms. The repo ships the full builder (jax_rl/data_bridge/make_bc_dataset.py) so you can rebuild equivalent datasets from logs you obtain yourself.

License

MIT for these weights and the core training code. Note that the repo's evaluation bridge (jax_rl/mjai_bot/) links libriichi and is AGPL-3.0; see the repo's LICENSING.md.