DeepAI AI Chat
Log In Sign Up

Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning

by   Christoph Dann, et al.

We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the insight that, in order to achieve a favorable regret, an algorithm does not need to learn how to behave optimally in states that are not reached by an optimal policy. We prove tighter upper regret bounds for optimistic algorithms and accompany them with new information-theoretic lower bounds for a large class of MDPs. Our results show that optimistic algorithms can not achieve the information-theoretic lower bounds even in deterministic MDPs unless there is a unique optimal policy.


page 1

page 2

page 3

page 4


Cascaded Gaps: Towards Gap-Dependent Regret for Risk-Sensitive Reinforcement Learning

In this paper, we study gap-dependent regret guarantees for risk-sensiti...

Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs

This paper establishes that optimistic algorithms attain gap-dependent a...

Issues concerning realizability of Blackwell optimal policies in reinforcement learning

N-discount optimality was introduced as a hierarchical form of policy- a...

Online Model Selection for Reinforcement Learning with Function Approximation

Deep reinforcement learning has achieved impressive successes yet often ...

Self-guided Approximate Linear Programs

Approximate linear programs (ALPs) are well-known models based on value ...

Regret Bounds for Reinforcement Learning via Markov Chain Concentration

We give a simple optimistic algorithm for which it is easy to derive reg...

An Information-Theoretic Analysis of Bayesian Reinforcement Learning

Building on the framework introduced by Xu and Raginksy [1] for supervis...