Sample Efficient Actor-Critic with Experience Replay

Authors: Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih, Remi Munos, Koray Kavukcuoglu, Nando de Freitas

Published: 2016 ()

Algorithm: ACER

arXiv: 1611.01224

Summary

Abstract

This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems. To achieve this, the paper introduces several innovations, including truncated importance sampling with bias correction, stochastic dueling network architectures, and a new trust region policy optimization method.

Links

Primary

Paper arxiv.org

Standard

arXiv Abstract 1611.01224 arXiv PDF 1611.01224 arXiv HTML 1611.01224