# Exploration--Exploitation in MDPs with Options

arXiv: https://arxiv.org/abs/1703.08667 · HTML: https://mlsanity.com/paper/1703.08667/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2017.

## Built on by (most cited first, 19 of 19)

- [Temporal Abstraction in Reinforcement Learning with the Successor Representation](https://mlsanity.com/paper/2110.05740/) (2021)
- [On the Importance of Exploration for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2306.05483/) (2023)
- [A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs](https://mlsanity.com/paper/2306.03236/) (2023)
- [Provable Hierarchical Imitation Learning via EM](https://mlsanity.com/paper/2010.03133/) (2020)
- [Adjacency constraint for efficient hierarchical reinforcement learning](https://mlsanity.com/paper/2111.00213/) (2021)
- [LLM Augmented Hierarchical Agents](https://mlsanity.com/paper/2311.05596/) (2023)
- [Average-Reward Learning and Planning with Options](https://mlsanity.com/paper/2110.13855/) (2021)
- [Logarithmic regret bounds for continuous-time average-reward Markov decision processes](https://mlsanity.com/paper/2205.11168/) (2022)
- [Interactive Hierarchical Guidance using Language](https://mlsanity.com/paper/2110.04649/) (2021)
- [Provable Hierarchy-Based Meta-Reinforcement Learning](https://mlsanity.com/paper/2110.09507/) (2021)
- [Square-root regret bounds for continuous-time episodic Markov decision processes](https://mlsanity.com/paper/2210.00832/) (2022)
- [Learning Multi-agent Skills for Tabular Reinforcement Learning using Factor Graphs](https://mlsanity.com/paper/2201.08227/) (2022)
- [Towards an Interpretable Hierarchical Agent Framework using Semantic Goals](https://mlsanity.com/paper/2210.08412/) (2022)
- [Goal Exploration Augmentation via Pre-trained Skills for Sparse-Reward Long-Horizon Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2210.16058/) (2022)
- [ASC me to Do Anything: Multi-task Training for Embodied AI](https://mlsanity.com/paper/2202.06987/) (2022)
- [Hierarchical Average-Reward Linearly-solvable Markov Decision Processes](https://mlsanity.com/paper/2407.06690/) (2024)
- [An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-Markov Decision Processes](https://mlsanity.com/paper/2305.06936/) (2023)
- [Realizable Abstractions: Near-Optimal Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2512.04958/) (2025)
- [Hierarchical Behaviour Spaces](https://mlsanity.com/paper/2604.24558/) (2026)

## Abstract (arXiv)

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 textitprovably much smaller than the regret suffered when learning with primitive actions.