English

Learning State Abstractions for Transfer in Continuous Control

Machine Learning 2020-02-14 v1 Artificial Intelligence Machine Learning

Abstract

Can simple algorithms with a good representation solve challenging reinforcement learning problems? In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good representations" to be a learned state abstraction, and "challenging problems" to be continuous control tasks. Our main contribution is a learning algorithm that abstracts a continuous state-space into a discrete one. We transfer this learned representation to unseen problems to enable effective learning. We provide theory showing that learned abstractions maintain a bounded value loss, and we report experiments showing that the abstractions empower tabular Q-Learning to learn efficiently in unseen tasks.

Keywords

Cite

@article{arxiv.2002.05518,
  title  = {Learning State Abstractions for Transfer in Continuous Control},
  author = {Kavosh Asadi and David Abel and Michael L. Littman},
  journal= {arXiv preprint arXiv:2002.05518},
  year   = {2020}
}
R2 v1 2026-06-23T13:40:48.717Z