off-policy 开源项目推荐（54 个）

MishaLaskin /curl

CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

TianhongDai /hindsight-experience-replay

这是Hindsight Experience Replay（HER）的pytorch实现——在所有取物机器人环境中进行实验。

denisyarats /drq

DrQ: Data regularized Q

MishaLaskin /rad

RAD: Reinforcement Learning with Augmented Data

instadeepai /flashbax

⚡ Flashbax: Accelerated Replay Buffers in JAX

denisyarats /exorl

ExORL: Exploratory Data for Offline Reinforcement Learning

pokaxpoka /sunrise

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

zhihanyang2022 /off-policy-continuous-control

Official PyTorch code for "Recurrent Off-policy Baselines for Memory-based Continuous Control" (DeepRL Workshop, NeurIPS 21)

Trenza1ore /sb3-extra-buffers

[ 👾 ] ➡️ 💾 ➡️ { 🎮🕹️ } Extra Stable-Baselines3 buffer classes. Reducing RL memory usage drastically with minimal overhead.

baturaysaglam /actor-prioritized-exp-replay

Actor Prioritized Experience Replay

Infini-AI-Lab /jackpot

A rejection-sampling based distribution alignment method for extreme actor-policy mismatch RL Training

MohammadAsadolahi /Reinforcement-Learning-solving-a-simple-4by4-Gridworld-using-Qlearning-in-python

solving a simple 4*4 Gridworld almost similar to openAI gym FrozenLake using Qlearning Temporal difference method Reinforcement Learning

zZhiG /RLPD-PyTorch

off-policy algorithm utilizing offline and online data

Rosefintech /Rosefintech-RosefinAIEngine

RosefinAIEngine of Rosfintech

lionelblonde /sam-tf

TensorFlow implementation of "Sample-efficient Imitation Learning via Generative Adversarial Nets"

lionelblonde /sam-pytorch

PyTorch implementation of "Sample-efficient Imitation Learning via Generative Adversarial Nets"

baturaysaglam /AC-Off-POC

Off-Policy Correction for Actor-Critic Algorithms in Deep Reinforcement Learning

bmaxdk /DeepRL-ND-Continuous-Control

DDPG and D4PG Continuous Control

narjesno /Reinforcement-Learning

This repository contains all of the Reinforcement Learning-related projects I've worked on. The projects are part of the graduate course at the University of Tehran.

cbanerji /Sample_efficient_RL.

Collection of codes pertaining to my research in model-free RL algorithms.