Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning

1 code implementation • NeurIPS 2023 • Sotetsu Koyamada, Shinri Okano, Soichiro Nishimori, Yu Murata, Keigo Habara, Haruka Kita, Shin Ishii

We propose Pgx, a suite of board game reinforcement learning (RL) environments written in JAX and optimized for GPU/TPU accelerators.

reinforcement-learning Reinforcement Learning (RL)

Convergence analysis and acceleration of the smoothing methods for solving extensive-form games

no code implementations • 20 Mar 2023 • Keigo Habara, Ellen Hidemi Fukuda, Nobuo Yamashita

It can represent games with multiple decision points and incomplete information, and hence it is helpful in formulating games with uncertain inputs, such as poker.