Exploration--Exploitation in MDPs with Options

2017/03/25 by Ronan Fruit, Fruit, Ronan, Alessandro Lazaric +1 · 3 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #Game Theory and Applications #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1703.08667

openalex publication_date 2017/03/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

While a large body of empirical results show that temporally-extended actions and options may significantly affect the learning performance of an agent, the theoretical understanding of how and when options can be beneficial in online reinforcement learning is relatively limited. In this paper, we derive an upper and lower bound on the regret of a variant of UCRL using options. While we first analyze the algorithm in the general case of semi-Markov decision processes (SMDPs), we show how these results can be translated to the specific case of MDPs with options and we illustrate simple scenarios in which the regret of learning with options can be provably much smaller than the regret suffered when learning with primitive actions.

Cited by

• Realizable Abstractions: Near-Optimal Hierarchical Reinforcement Learning
• Provable Hierarchy-Based Meta-Reinforcement Learning
• Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation

Related

• An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-Markov Decision Processes
• Average-Reward Learning and Planning with Options
• A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning
• The regret lower bound for communicating Markov Decision Processes
• Near-optimal Reinforcement Learning in Factored MDPs