Symbolic State Partitioning for Reinforcement Learning

TL;DR

This paper introduces a symbolic state partitioning method for reinforcement learning that improves efficiency and policy reliability by better capturing environment dynamics, especially in sparse reward settings.

Contribution

The paper presents a novel symbolic partitioning approach derived from environment dynamics, enhancing state space coverage and learning performance in reinforcement learning.

Findings

Symbolic partitioning improves state space coverage.

Enhanced learning performance with sparse rewards.

Better scalability and precision in state space representation.

Abstract

Tabular reinforcement learning methods cannot operate directly on continuous state spaces. One solution for this problem is to partition the state space. A good partitioning enables generalization during learning and more efficient exploitation of prior experiences. Consequently, the learning process becomes faster and produces more reliable policies. However, partitioning introduces approximation, which is particularly harmful in the presence of nonlinear relations between state components. An ideal partition should be as coarse as possible, while capturing the key structure of the state space for the given problem. This work extracts partitions from the environment dynamics by symbolic execution. We show that symbolic partitioning improves state space coverage with respect to environmental behavior and allows reinforcement learning to perform better for sparse rewards. We evaluate symbolic state space partitioning with respect to precision, scalability, learning agent performance and state space coverage for the learnt policies.