Bounding the Optimal Value Function in Compositional Reinforcement Learning
Publication Date
1-1-2023
Document Type
Conference Proceeding
Publication Title
Proceedings of Machine Learning Research
Volume
216
First Page
22
Last Page
32
Abstract
In the field of reinforcement learning (RL), agents are often tasked with solving a variety of problems differing only in their reward functions. In order to quickly obtain solutions to unseen problems with new reward functions, a popular approach involves functional composition of previously solved tasks. However, previous work using such functional composition has primarily focused on specific instances of composition functions whose limiting assumptions allow for exact zero-shot composition. Our work unifies these examples and provides a more general framework for compositionality in both standard and entropy-regularized RL. We find that, for a broad class of functions, the optimal solution for the composite task of interest can be related to the known primitive task solutions. Specifically, we present double-sided inequalities relating the optimal composite value function to the value functions for the primitive tasks. We also show that the regret of using a zero-shot policy can be bounded for this class of functions. The derived bounds can be used to develop clipping approaches for reducing uncertainty during training, allowing agents to quickly adapt to new tasks.
Funding Number
2246221
Funding Sponsor
National Science Foundation
Department
Computer Engineering
Recommended Citation
Jacob Adamczyk, Volodymyr Makarenko, Argenis Arriojas, Stas Tiomkin, and Rahul V. Kulkarni. "Bounding the Optimal Value Function in Compositional Reinforcement Learning" Proceedings of Machine Learning Research (2023): 22-32.
