<
8000
div class="container-xl px-3 px-md-4 px-lg-5">
nissymori
Follow
{{ message }}
Stars
Clean single-file implementation of offline RL algorithms in JAX
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
[RLC 2025] Official code repository for "Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps"
Official implementation for "How Should We Meta-Learn Reinforcement Learning Algorithms?"
[TMLR 2025] Importance Weighting for Aligning Language Models under Deployment Distribution Shift
Implementation for our COLM paper "Off-Policy Corrected Reward Modeling for RLHF"
Simplifying reinforcement learning for complex game environments
Ludax is a domain-specific language for board games that automatically compiles into hardware-accelerated learning environments with the JAX library
textlintプリセット：AIっぽい記述パターンを検出し、より自然な日本語表現を促すルール集
An Agent-Environment interface with Jax transformation compatibility
[ICML 2025] Official code repository for "Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning"
Policy-based Riichi Mahjong(立直麻将) AI, based on Mortal and Suphx, powered by Rust and deep RL.
Code for the paper "Practical estimation of the optimal classification error with soft labels and calibration"
Implementation of Soft Actor Critic and some of its improvements in Pytorch
Code for Posterior Sampling for Deep Reinforcement Learning, ICML 2023
Unified Implementations of Offline Reinforcement Learning Algorithms
Authors' implementation of the "Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?"
WandererXII / lishogi
Forked from lichess-org/lila☗ lishogi.org: the forever free, adless and open source shogi server forked from lichess.org ☗
[CVPR2025] Official PyTorch implimentation for "Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment"
YaneuraOu is the World's Strongest Shogi engine(AI player) , WCSC29 1st winner , educational and USI compliant engine.
MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.
🚀🀄️ A fast and strong AI for riichi mahjong, powered by Rust and deep reinforcement learning.
A curated list of Diffusion Model in RL resources (continually updated)