Improving the efficiency of Bayesian inverse reinforcement learning
Name
How_Improving the efficiency of Bayesian.pdf
Size
409.04 KB
Format
Adobe PDF
Checksum (MD5)
0cecdcaa62d9c83b91e4ef0929fff29c
Author(s)
How, Jonathan P.
Michini, Bernard J.
Date Issued
May 2012
Journal
Proceedings of the 2012 IEEE International Conference on Robotics and Automation
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Michini, Bernard, and Jonathan P. How. “Improving the efficiency of Bayesian inverse reinforcement learning.” In 2012 IEEE International Conference on Robotics and Automation, 3651-3656. Institute of Electrical and Electronics Engineers, 2012.
Version
Author's final manuscript
Abstract
Inverse reinforcement learning (IRL) is the task of learning the reward function of a Markov Decision Process (MDP) given knowledge of the transition function and a set of expert demonstrations. While many IRL algorithms exist, Bayesian IRL [1] provides a general and principled method of reward learning by casting the problem in the Bayesian inference framework. However, the algorithm as originally presented suffers from several inefficiencies that prohibit its use for even moderate problem sizes. This paper proposes modifications to the original Bayesian IRL algorithm to improve its efficiency and tractability in situations where the state space is large and the expert demonstrations span only a small portion of it. The key insight is that the inference task should be focused on states that are similar to those encountered by the expert, as opposed to making the naive assumption that the expert demonstrations contain enough information to accurately infer the reward function over the entire state space. A modified algorithm is presented and experimental results show substantially faster convergence while maintaining the solution quality of the original method.
MIT Department
Massachusetts Institute of Technology. Aerospace Controls Laboratory
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike 3.0
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ICRA.2012.6225241
