The Limits of Temporal Abstractions for Reinforcement Learning with Sparse Rewards
Name
li-zli11010-meng-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
1.22 MB
Format
Adobe PDF
Checksum (MD5)
811c44e46875da8eaa0d90ac6d9ff6f8
Author(s)
Li, Zhening
Advisor(s)
Solar-Lezama, Armando
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, there has been little theoretical work aimed to characterize these properties precisely. This work studies the utility of skills in sparse-reward environments with a discrete state space and finite action space. We show, both theoretically and empirically, that RL performance gains from skills are worse in environments where successful trajectories are less compressible. In environments with a highly incompressible distribution of successful trajectories, using unexpressive skills such as macroactions will provably worsen RL performance. We hope our findings can guide research on automatic skill discovery and help RL practitioners better decide when and how to use skills.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
