LGAIJan 8, 2023

Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior

arXiv:2301.02952v17 citationsh-index: 60
Originality Incremental advance
AI Analysis

This addresses the challenge of sparse rewards in RL for non-Markovian domains, offering an incremental improvement by automating a previously manual step.

The paper tackles the problem of learning complex, temporally extended behaviors in reinforcement learning with sparse rewards by automatically discovering symbolic state abstractions, resulting in an algorithm that learns optimal policies with significantly fewer environment samples than state-of-the-art RL methods.

Many real-world reinforcement learning (RL) problems necessitate learning complex, temporally extended behavior that may only receive reward signal when the behavior is completed. If the reward-worthy behavior is known, it can be specified in terms of a non-Markovian reward function - a function that depends on aspects of the state-action history, rather than just the current state and action. Such reward functions yield sparse rewards, necessitating an inordinate number of experiences to find a policy that captures the reward-worthy pattern of behavior. Recent work has leveraged Knowledge Representation (KR) to provide a symbolic abstraction of aspects of the state that summarize reward-relevant properties of the state-action history and support learning a Markovian decomposition of the problem in terms of an automaton over the KR. Providing such a decomposition has been shown to vastly improve learning rates, especially when coupled with algorithms that exploit automaton structure. Nevertheless, such techniques rely on a priori knowledge of the KR. In this work, we explore how to automatically discover useful state abstractions that support learning automata over the state-action history. The result is an end-to-end algorithm that can learn optimal policies with significantly fewer environment samples than state-of-the-art RL on simple non-Markovian domains.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes