reinforcement-learning

Keras Implementation of popular Deep RL Algorithms (A3C, DDQN, DDPG, Dueling DDQN)

Long-Term Evolution Project of Reinforcement Learning

Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.

This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch

LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)

A universal flight control tuning framework

The official code repository supporting the book, Grokking Artificial Intelligence Algorithms

Gym Electric Motor (GEM): An OpenAI Gym Environment for Electric Motors

Sokoban environment for OpenAI Gym

This is the official repository for the book Transformers - The Definitive Guide

A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementations with an aim to improve accessibility in RL

SkyText是由奇点智源发布的中文GPT3预训练大模型，可以进行文章续写、对话、中英翻译、内容风格生成、推理、诗词对联等不同任务。| SkyText is a Chinese GPT3 pre-trained large model released by Singularity-AI, which can perform different tasks such as chatting, Q&A, and Chinese-English translation.

[ICLR 2026] VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning

A Japanese (Riichi) Mahjong AI Framework

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion

Implementation for FP8/INT8 Rollout for RL training without performence drop.

Codebase of GRPO: Implementations and Resources of GRPO and Its Variants

Train a Language Model with GRPO to create a schedule from a list of events and priorities

Enhancing LLMs with LoRA