DisCoRL: Continual Reinforcement Learning via Policy Distillation
arXiv:1907.05855
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.
arXiv admin note: text overlap with arXiv:1906.04452
References in corpus (1)
Cited by in corpus (4)
- Continuum: Simple Management of Complex Continual Learning Scenarios
- Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
- DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics
- A Simple Approach to Continual Learning by Transferring Skill Parameters