Generalized Representation Learning Methods for Deep Reinforcement Learning

Zhu, Hanhua

doi:10.24963/IJCAI.2020/748

Generalized Representation Learning Methods for Deep Reinforcement Learning

Hanhua Zhu

IJCAI 2020 pp. 5216-5217

doi:10.24963/IJCAI.2020/748 /ijcai/2020/zhu2020ijcai-generalized/

Abstract

Deep reinforcement learning (DRL) increases the successful applications of reinforcement learning (RL) techniques but also brings challenges such as low sample efficiency. In this work, I propose generalized representation learning methods to obtain compact state space suitable for RL from a raw observation state. I expect my new methods will increase sample efficiency of RL by understandable representations of state and therefore improve the performance of RL.

PDF IJCAI Semantic Scholar

Cite

Text

Zhu. "Generalized Representation Learning Methods for Deep Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2020. doi:10.24963/IJCAI.2020/748

Markdown

[Zhu. "Generalized Representation Learning Methods for Deep Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2020.](https://mlanthology.org/ijcai/2020/zhu2020ijcai-generalized/) doi:10.24963/IJCAI.2020/748

BibTeX

@inproceedings{zhu2020ijcai-generalized,
  title     = {{Generalized Representation Learning Methods for Deep Reinforcement Learning}},
  author    = {Zhu, Hanhua},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {5216-5217},
  doi       = {10.24963/IJCAI.2020/748},
  url       = {https://mlanthology.org/ijcai/2020/zhu2020ijcai-generalized/}
}