94
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Policy Distillation

      Preprint

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          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.

          Related collections

          Author and article information

          Journal
          2015-11-19
          2016-01-07
          Article
          1511.06295
          99bac182-b7b6-4e92-8407-d84752a255b7

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          Submitted to ICLR 2016
          cs.LG

          Artificial intelligence
          Artificial intelligence

          Comments

          Comment on this article