hindsight-experience-replay 开源项目推荐（43 个）

sudharsan13296 /Hands-On-Reinforcement-Learning-With-Python

使用 OpenAI Gym 和 TensorFlow 掌握强化学习与深度强化学习。

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。

jangirrishabh /Overcoming-exploration-from-demos

Implementation of the paper "Overcoming Exploration in Reinforcement Learning with Demonstrations" Nair et al. over the HER baselines from OpenAI

kaymen99 /Robot-arm-control-with-RL

使用强化学习算法控制机械臂：带事后经验回放（HER）的 DDPG 和 TD3

akazemipour /DDPG-HER

实施深层决定性政策梯度与事后诸葛亮经验回放。

alphadl /AgentHER

AgentHER：LLM代理的事后诸葛亮体验回放

YangRui2015 /Sparse-Reward-Algorithms

Implement many Sparse Reward algorithms in Gym Fetch environment

med-air /DEX

[ICRA 2023] Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot

hemilpanchiwala /Hindsight-Experience-Replay

Implementation of HindSight Experience Replay paper with Pytorch

YangRui2015 /AWGCSL

Code for ICLR 2022 paper Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RL.

KanishkNavale /Trajectory-Planning-using-HER-and-Reward-Engineering

Trajectory planning based on RL with Hindsight Experience Replay & Dense Reward Engineering to solve openai-gym robotics "FetchReach-v1" environment using TF2 & PyTorch

monoelh /deep-reinforcement-learning_DDQN_PPO_HER

MLP-framework (pure numpy) and DDQN-framework for OpenAI's Gym games. +test code for PPO added. +Hindsight Experience Replay(HER) bitflip-DQN example. +prioritized replay.

med-air /ViSkill

[IROS 2023] Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot

kwea123 /hindsight_experience_replay

A tensorflow implementation of hindsight experience replay

mfornet /hindsight-experience-replay

Implementation of HER algorithm in the bit-flipping environment.

YangRui2015 /Modular_HER

Modular-HER is revised from OpenAI baselines and supports many improvements for Hindsight Experience Replay as modules.

holarissun /PCHID_code

Code for [NeurIPS'2019 Spotlight] Policy Continuation with Hindsight Inverse Dynamics

TaoHuang13 /hindsight-experience-replay-with-demo

PyTorch implementation of the paper Overcoming Exploration in Reinforcement Learning with Demonstrations in surgical robot manipulation tasks.

SioKCronin /Hindsight-Experience-Replay

PPO with Hindsight Experience Replay (HER)

jimimvp /torch_rl

Reinforcement learning library for PyTorch.