Skip to Main content Skip to Navigation
Conference papers

DISCORL: Continual reinforcement learning via policy distillation: A preprint

Abstract : In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the case of continual reinforcement learning a third challenge arises: learning tasks sequentially without forgetting the previous ones. In this paper, we tackle these challenges by proposing DisCoRL, an approach combining state representation learning and policy distillation. We experiment on a sequence of three simulated 2D navigation tasks with a 3 wheel omni-directional robot. Moreover, we tested our approach's robustness by transferring the final policy into a real life setting. The policy can solve all tasks and automatically infer which one to run.
Document type :
Conference papers
Complete list of metadata

Cited literature [43 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02381494
Contributor : Natalia Díaz-Rodríguez Connect in order to contact the contributor
Submitted on : Tuesday, November 26, 2019 - 4:13:33 PM
Last modification on : Wednesday, May 11, 2022 - 3:20:03 PM

File

NeurIPS19 DRL ws- DISCORL- CON...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02381494, version 1

Collections

Citation

René Traoré, Hugo Caselles-Dupré, Timothée Lesort, Te Sun, Guanghang Cai, et al.. DISCORL: Continual reinforcement learning via policy distillation: A preprint. NeurIPS workshop on Deep Reinforcement Learning, Dec 2019, Vancouver, Canada. ⟨hal-02381494⟩

Share

Metrics

Record views

80

Files downloads

101