Bias-Reduced Hindsight Experience Replay with Virtual Goal Prioritization (2019-05-14T00:00:00.000000Z)

TL;DR

This paper presents two improvements over the existing HER algorithm, which prioritize virtual goals from which the agent will learn more valuable information, and reduces existing bias in HER by the removal of misleading samples.

Authors

A. Biess

2 papers

Binyamin Manela

1 papers

Bias-Reduced Hindsight Experience Replay with Virtual Goal Prioritization

TL;DR

Authors

References16 items

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Energy-Based Hindsight Experience Prioritization

Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research

Proximal Policy Optimization Algorithms

Hindsight Experience Replay

Understanding deep learning requires rethinking generalization

OpenAI Gym

Prioritized Experience Replay

Continuous control with deep reinforcement learning

Universal Value Function Approximators

Playing Atari with Deep Reinforcement Learning

Reinforcement learning in robotics: A survey

MuJoCo: A physics engine for model-based control

Deep Learning

Reinforcement Learning and the Reward Engineering Principle

Reinforcement Learning: An Introduction

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL