√(n)-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank

by   Kefan Dong, et al.

In this paper, we consider the problem of online learning of Markov decision processes (MDPs) with very large state spaces. Under the assumptions of realizable function approximation and low Bellman ranks, we develop an online learning algorithm that learns the optimal value function while at the same time achieving very low cumulative regret during the learning process. Our learning algorithm, Adaptive Value-function Elimination (AVE), is inspired by the policy elimination algorithm proposed in (Jiang et al., 2017), known as OLIVE. One of our key technical contributions in AVE is to formulate the elimination steps in OLIVE as contextual bandit problems. This technique enables us to apply the active elimination and expert weighting methods from (Dudik et al., 2011), instead of the random action exploration scheme used in the original OLIVE algorithm, for more efficient exploration and better control of the regret incurred in each policy elimination step. To the best of our knowledge, this is the first √(n)-regret result for reinforcement learning in stochastic MDPs with general value function approximation.


page 1

page 2

page 3

page 4


Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints

We study regret minimization for infinite-horizon average-reward Markov ...

Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

We develop several new algorithms for learning Markov Decision Processes...

Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift

In this paper we revisit the method of off-policy corrections for reinfo...

Improved Algorithms for Misspecified Linear Markov Decision Processes

For the misspecified linear Markov decision process (MLMDP) model of Jin...

Active Exploration in Markov Decision Processes

We introduce the active exploration problem in Markov decision processes...

TopRank+: A Refinement of TopRank Algorithm

Online learning to rank is a core problem in machine learning. In Lattim...

Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses

Policy optimization is a widely-used method in reinforcement learning. D...