This is not the latest version of this item. The latest version can be found here.
Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning
Name
1909.05004.pdf
Description
Accepted version
Size
684.6 KB
Format
Adobe PDF
Checksum (MD5)
6f6ca0f5092c5619a8195087fe95b2a4
Author(s)
Kusari, Arpan
How, Jonathan P.
Date Issued
May 2020
Journal
Proceedings - IEEE International Conference on Robotics and Automation
Publisher
IEEE
Citation
Kusari, Arpan and How, Jonathan P. 2020. "Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning." Proceedings - IEEE International Conference on Robotics and Automation.
Version
Author's final manuscript
Abstract
© 2020 IEEE. A common approach for defining a reward function for multi-objective reinforcement learning (MORL) problems is the weighted sum of the multiple objectives. The weights are then treated as design parameters dependent on the expertise (and preference) of the person performing the learning, with the typical result that a new solution is required for any change in these settings. This paper investigates the relationship between the reward function and the optimal value function for MORL; specifically addressing the question of how to approximate the optimal value function well beyond the set of weights for which the optimization problem was actually solved, thereby avoiding the need to recompute for any particular choice. We prove that the value function transforms smoothly given a transformation of weights of the reward function (and thus a smooth interpolation in the policy space). A Gaussian process is used to obtain a smooth interpolation over the reward function weights of the optimal value function for three well-known examples: Gridworld, Objectworld and Pendulum. The results show that the interpolation can provide robust values for sample states and actions in both discrete and continuous domain problems. Significant advantages arise from utilizing this interpolation technique in the domain of autonomous vehicles: easy, instant adaptation of user preferences while driving and true randomization of obstacle vehicle behavior preferences during training.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1109/icra40945.2020.9197456
