Fine-tune LLM agents with online reinforcement learning

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

PyTorch implementation of Soft Actor-Critic (SAC)

Codebase of ηψ-Learning algorithm that learns a non-Markovian maximum state entropy exploration policy by combining predecessor and successor representation to estimate the state visitation distrib…

PyTorch implementation of GAIL and AIRL based on PPO.

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

Code for the paper "Exploration by Random Network Distillation"

Representation Learning for RL

An elegant PyTorch deep reinforcement learning library.

PyTorch implementations of deep reinforcement learning algorithms and environments

Reinforcement Learning in PyTorch

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

DEPRECATED: Open-source software for robot simulation, integrated with OpenAI Gym.

This repo is intended as an extension for OpenAI Gym for auxiliary tasks (multitask learning, transfer learning, inverse reinforcement learning, etc.)

Official repo for the E3B algorithm described in the paper "Exploration via Elliptical Episodic Bonuses".

Repository for our ICLR 2023 paper: DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems

Gym reinforcement learning environment for OpenCat robots.

Implement many Sparse Reward algorithms in Gym Fetch environment

A JAX Implementation of the Twin Delayed DDPG Algorithm

PyTorch implementation of Soft-Actor-Critic and Prioritized Experience Replay (PER) + Emphasizing Recent Experience (ERE) + Munchausen RL + D2RL and parallel Environments.

Author's PyTorch implementation of LAP and PAL with TD3 and DDQN

Lightweight and scalable framework for Reinforcement Learning

Public repo for HF blog posts

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

🔥数据科学竞赛 Baseline & Topline

Official implementation for "Anti-Exploration by Random Network Distillation", ICML 2023

A lightweight reimplementation of Adversarially Trained Actor Critic

Code accompanying the paper Adversarially Trained Actor Critic for Offline Reinforcement Learning by Ching-An Cheng*, Tengyang Xie*, Nan Jiang, and Alekh Agarwal.

AGAC: Adversarially Guided Actor-Critic