Sample Efficient Actor-Critic with Experience Replay

@article{Wang2016SampleEA,
  title={Sample Efficient Actor-Critic with Experience Replay},
  author={Ziyu Wang and Victor Bapst and Nicolas Heess and Volodymyr Mnih and R{\'e}mi Munos and Koray Kavukcuoglu and Nando de Freitas},
  journal={CoRR},
  year={2016},
  volume={abs/1611.01224}
}
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. 
Highly Influential
This paper has highly influenced 13 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 177 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 6 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 105 extracted citations

On-policy Trust Region Policy Optimisation

REPLAY BUFFERS
2018
View 5 Excerpts
Highly Influenced

Sample Efficient Deep Reinforcement Learning for Dialogue Systems With Large Action Spaces

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2018
View 10 Excerpts
Highly Influenced

Self-Imitation Learning

View 5 Excerpts
Highly Influenced

Value Propagation Networks

View 3 Excerpts
Highly Influenced

178 Citations

050100150201720182019
Citations per Year
Semantic Scholar estimates that this publication has 178 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 25 references

Off-Policy Actor-Critic

View 4 Excerpts
Highly Influenced

Prioritized Experience Replay

View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…