ReBeL
AlphaZero for hidden-information games — the poker code stayed locked
Latest: NeurIPS 2020 paper + open-source Liar's Dice code (December 2020)
Recursive Belief-based Learning: a general RL-plus-search algorithm extending AlphaZero-style self-play to imperfect-information games by operating on public belief states. ReBeL reached superhuman heads-up no-limit hold'em with far less poker-specific knowledge than prior bots. Meta open-sourced a Liar's Dice implementation alongside the NeurIPS 2020 paper.
Why it matters
Extended AlphaZero-style self-play plus search to imperfect-information games by operating on public belief states, reaching superhuman heads-up no-limit hold'em with far less poker-specific knowledge than earlier bots. The Apache-licensed Liar's Dice implementation, with released value-function checkpoints, is the accessible entry point.
Facts
- By converting hidden-information games into continuous-state perfect-information games over beliefs, ReBeL unified the AlphaZero and Pluribus research lines — the poker code itself was withheld to protect online games, so Liar's Dice became the open testbed.
Try it yourself
Code and checkpoints on GitHub ↗ Read the paper ↗ NeurIPS 2020 proceedings page ↗
Lineage
Sources
arXiv ↗GitHub · rebel ↗Meta AI blog ↗