Verifiable reinforcement learning via policy extraction
Name
7516-verifiable-reinforcement-learning-via-policy-extraction.pdf
Description
Published version
Size
889.83 KB
Format
Adobe PDF
Checksum (MD5)
0583c210919d82fd465059c8285046ea
Author(s)
Solar Lezama, Armando
Pu, Yewen
Bastani, Osbert
Date Issued
2018
Citation
Solar Lezama, Armando, Pu, Yewen and Bastani, Osbert. 2018. "Verifiable reinforcement learning via policy extraction."
Version
Final published version
Abstract
© 2018 Curran Associates Inc.All rights reserved. While deep reinforcement learning has successfully solved many challenging control tasks, its real-world applicability has been limited by the inability to ensure the safety of learned policies. We propose an approach to verifiable reinforcement learning by training decision tree policies, which can represent complex policies (since they are nonparametric), yet can be efficiently verified using existing techniques (since they are highly structured). The challenge is that decision tree policies are difficult to train. We propose VIPER, an algorithm that combines ideas from model compression and imitation learning to learn decision tree policies guided by a DNN policy (called the oracle) and its Q-function, and show that it substantially outperforms two baselines. We use VIPER to (i) learn a provably robust decision tree policy for a variant of Atari Pong with a symbolic state space, (ii) learn a decision tree policy for a toy game based on Pong that provably never loses, and (iii) learn a provably stable decision tree policy for cart-pole. In each case, the decision tree policy achieves performance equal to that of the original DNN policy.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/7516-verifiable-reinforcement-learning-via-policy-extraction
