Policy Distillation
Abstract
Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve good performance. In this work, we present a novel method called policy distillation that can be used to extract the policy of a reinforcement learning agent and train a new network that performs at the expert level while being dramatically smaller and more efficient. Furthermore, the same method can be used to consolidate multiple task-specific policies into a single policy. We demonstrate these claims using the Atari domain and show that the multi-task distilled agent outperforms the single-task teachers as well as a jointly-trained DQN agent.
- Publication:
-
arXiv e-prints
- Pub Date:
- November 2015
- DOI:
- 10.48550/arXiv.1511.06295
- arXiv:
- arXiv:1511.06295
- Bibcode:
- 2015arXiv151106295R
- Keywords:
-
- Computer Science - Machine Learning
- E-Print:
- Submitted to ICLR 2016