Soichiro Nishimori

JAX-CORL. Clean single-file implementation of offline RL algorithms in JAX

mahjax. A GPU-Accelerated Mahjong Simulator for RL in JAX

remax-rl. [ICML2026] Official JAX code for Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying

SymPO. [TMLR2026] Official code for "On Symmetric Losses for Policy Optimization with Noisy Preferences"

PUORL. [RLC2025] Official code for "Offline Reinforcement Learning with Domain-Unlabeled Data"

nissymori.github.io. HTML

ReMAC. The Official JAX Code for "Retry Policy Gradients for Continuous Action Spaces"