Log In Sign Up

Adaptive Discretization in Online Reinforcement Learning

by   Sean R. Sinclair, et al.

Discretization based approaches to solving online reinforcement learning problems have been studied extensively in practice on applications ranging from resource allocation to cache management. Two major questions in designing discretization-based algorithms are how to create the discretization and when to refine it. While there have been several experimental results investigating heuristic solutions to these questions, there has been little theoretical treatment. In this paper we provide a unified theoretical analysis of tree-based hierarchical partitioning methods for online reinforcement learning, providing model-free and model-based algorithms. We show how our algorithms are able to take advantage of inherent structure of the problem by providing guarantees that scale with respect to the 'zooming dimension' instead of the ambient dimension, an instance-dependent quantity measuring the benignness of the optimal Q_h^⋆ function. Many applications in computing systems and operations research requires algorithms that compete on three facets: low sample complexity, mild storage requirements, and low computational burden. Our algorithms are easily adapted to operating constraints, and our theory provides explicit bounds across each of the three facets. This motivates its use in practical applications as our approach automatically adapts to underlying problem structure even when very little is known a priori about the system.


page 1

page 2

page 3

page 4


Adaptive Discretization for Model-Based Reinforcement Learning

We introduce the technique of adaptive discretization to design efficien...

Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces

We present an efficient algorithm for model-free episodic reinforcement ...

Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation

Myopic exploration policies such as epsilon-greedy, softmax, or Gaussian...

Bridging the Gap between Reinforcement Learning and Knowledge Representation: A Logical Off- and On-Policy Framework

Knowledge Representation is important issue in reinforcement learning. I...

Online Model Selection for Reinforcement Learning with Function Approximation

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

The Teaching Dimension of Q-learning

In this paper, we initiate the study of sample complexity of teaching, t...

Cache Allocation in Multi-Tenant Edge Computing via online Reinforcement Learning

We consider in this work Edge Computing (EC) in a multi-tenant environme...