Sample Efficient Actor-Critic with Experience Replay
2016-11-03Code Available1· sign in to hype
Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih, Remi Munos, Koray Kavukcuoglu, Nando de Freitas
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/Kaixhin/ACERpytorch★ 258
- github.com/dchetelat/acerpytorch★ 0
- github.com/PaulCharnay/Projet_AIFnone★ 0
- github.com/opendilab/DI-engine/blob/main/ding/policy/acer.pypytorch★ 0
- github.com/neilsgp/RL-Algorithmsnone★ 0
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.