Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge
Name
alharbi-meshal-csesm-ccse-2024-thesis Meshal Alharbi.pdf
Description
Thesis PDF
Size
1.84 MB
Format
Adobe PDF
Checksum (MD5)
07ab6c6742d3f29f061ae96d3c2d8089
Author(s)
Alharbi, Meshal
Advisor(s)
Roozbehani, Mardavij
Dahleh, Munther A.
Date Issued
May 2024
Publisher
Massachusetts Institute of Technology
Abstract
The problem of sample complexity of online reinforcement learning is often studied in the literature without taking into account any partial knowledge about the system dynamics that could potentially accelerate the learning process. In this thesis, we study the sample complexity of online Q-learning methods when some prior knowledge about the dynamics is available or can be learned efficiently. We focus on systems that evolve according to an additive disturbance model where the underlying dynamics are described by a deterministic function of states and actions, along with an unknown additive disturbance that is independent of states and actions. In the setting of finite Markov decision processes, we present an optimistic Q-learning algorithm that achieves Õ(√T) regret without polynomial dependency on the number of states and actions under perfect knowledge of the dynamics function. This is in contrast to the typical Õ(√SAT) regret for existing Q-learning methods. Further, if only a noisy estimate of the dynamics function is available, our method can learn an approximately optimal policy in a number of samples that is independent of the cardinalities of state and action spaces. The sub-optimality gap depends on the approximation error of the noisy estimate, as well as the Lipschitz constant of the corresponding optimal value function. Our approach does not require modeling of the transition probabilities and enjoys the same memory complexity as model-free methods.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Center for Computational Science and Engineering
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
