# Learning State Abstractions for Transfer in Continuous Control

arXiv: https://arxiv.org/abs/2002.05518 · HTML: https://mlsanity.com/paper/2002.05518/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2020.

## Built on by (most cited first, 3 of 3)

- [The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents](https://mlsanity.com/paper/2107.05686/) (2021)
- [Behavior Prior Representation learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2211.00863/) (2022)
- [Using Human-Guided Causal Knowledge for More Generalized Robot Task Planning](https://mlsanity.com/paper/2110.04664/) (2021)

## Abstract (arXiv)

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.