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.
@article{arxiv.1511.06295,
title = {Policy Distillation},
author = {Andrei A. Rusu and Sergio Gomez Colmenarejo and Caglar Gulcehre and Guillaume Desjardins and James Kirkpatrick and Razvan Pascanu and Volodymyr Mnih and Koray Kavukcuoglu and Raia Hadsell},
journal= {arXiv preprint arXiv:1511.06295},
year = {2016}
}