gvsolver

Superhuman No-Limit Hold'em in real-time.

Poker is a notoriously hard game to solve: a vast action space, imperfect information, and stochastic outcomes.

Two AIs have played No-Limit Hold'em at a superhuman level: Libratus¹ for heads-up, and Pluribus² for six-max. Both made the cover of Science. Both came out of Carnegie Mellon, built by academics rather than poker professionals — and demonstrated in controlled matches against invited players, not in the games where the world's strongest players actually compete.

gvsolver was born of the question: How would a production-grade, low-latency solution look, built for the toughest games online?

gvsolver is a superhuman poker AI for No-Limit Hold'em. It runs on commodity hardware, returns solutions in under five seconds, and produces strategies with sub-1% exploitability against expert abstractions.

Stack

• CFR engine Vector-form CFR+³: regret-matching+ clipping, linearly-weighted averaging, alternating updates. Empirical convergence is roughly O(1/t) versus O(1/√t) for vanilla CFR, and the vector form processes the full hand range at each node in one SIMD pass.
• Blueprint strategy 100TB of pre-computed solutions with hand-tuned tree construction and abstractions.
• Real-time subgame solving At runtime we anchor on the blueprint and re-solve the live subgame with updated gamestate including out-of-distribution actions.
• Vision & OCR layer Custom vision and OCR models, trained per-site, detect the live game state directly from screen capture.

End-to-end, gvsolver detects the live game state, solves it, and returns a sub-1% exploitability strategy in under five seconds, autonomously.

Access

€6,000 per seat per month. Currently no seats open.

Closing

We no longer operate commercially. From the beginning, our motivation was to solve poker in real-time and reach superhuman performance in the actual most competitive games in the world. We accomplished this mission.

1. Brown, N., Sandholm, T. (2018). Superhuman AI for heads-up no-limit poker: Libratus beats top professionals. Science 359 (6374), 418–424.
2. Brown, N., Sandholm, T. (2019). Superhuman AI for multiplayer poker. Science 365 (6456), 885–890.
3. Zinkevich, M., Johanson, M., Bowling, M., Piccione, C. (2007). Regret Minimization in Games with Incomplete Information. NeurIPS.