Projects related to Annual Computer Poker Competition

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

🤖 An Open Source Texas Hold'em AI

Poker-Hand-Evaluator: An efficient poker hand evaluation algorithm and its implementation, supporting 7-card poker and Omaha poker evaluation

BibTool is a tool for manipulating BibTeX data bases. BibTeX provides a mean to integrate citations into LaTeX documents. BibTool allows the manipulation of BibTeX files which goes beyond the possi…

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Partially Observable Process Gym

verl: Volcano Engine Reinforcement Learning for LLMs

SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters (ICLR 2025)

Hackable and optimized Transformers building blocks, supporting a composable construction.

Active reward modeling with last layer Fisher Information (ICML'25)

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

Codebase for Paper Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs

Self-playing Adversarial Language Game Enhances LLM Reasoning, NeurIPS 2024

Reusable BatchBALD implementation

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

AlphaFold 3 inference pipeline.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and Alternatives