- Delete ARCHITECTURE_HAND_LOGGING_TOURNAMENT_IMPROVEMENTS.md (implemented) - Delete ARCHITECTURE_SUPERSONIC_EVALUATOR.md (implemented) - Delete REFERENCES.md (no longer needed) - Simplify ROADMAP.md: remove Phases 4-7 (live server, advanced bots) - Simplify VISION.md: focus on simulation testbed only - Update README.md: dual evaluator architecture, fix broken links - Update holdem_core/README.md: fix title, add Supersonic evaluator docs
585 B
585 B
Poker AI Simulation Testbed
- Configurable bots (Rule-based, Nash EQ, Statistical, Hand-reading, Reinforcement Learning)
- Mass parallel simulations with GPU acceleration (e.g., for turn and river rollouts)
- Multi-tier hand evaluation: Supersonic LUT trie → Cactus Kev perfect-hash → Algorithmic fallback, with DashMap-cached 7-card evaluation
- TOML-driven configuration for all parameters of bots and simulations
- Comprehensive result analysis and bot evolution
Expected Outcomes
- Research Platform: Systematic testing of poker AI strategies