Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
The general sequential decision-making problem, which includes Markov decision processes (MDPs) and partially observable MDPs (POMDPs) as special cases, aims at maximizing a cumulative reward by making a sequence of decisions based on a history of observations and actions over time. Recent studies have shown that the sequential decision-making problem is statistically learnable if it admits a low-rank structure modeled by predictive state representations (PSRs). Despite these advancements, existing approaches typically involve oracles or steps that are computationally intractable. On the other hand, the upper confidence bound (UCB) based approaches, which have served successfully as computationally efficient methods in bandits and MDPs, have not been investigated for more general PSRs, due to the difficulty of optimistic bonus design in these more challenging settings. This paper proposes the first known UCB-type approach for PSRs, featuring a novel bonus term that upper bounds the total variation distance between the estimated and true models. We further characterize the sample complexity bounds for our designed UCB-type algorithms for both online and offline PSRs. In contrast to existing approaches for PSRs, our UCB-type algorithms enjoy computational tractability, last-iterate guaranteed near-optimal policy, and guaranteed model accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyDecision MakingSequential Decision MakingSimilar Papers 제목 키워드 기반
Revisiting Locality in Binary-Integer Representations
Mutation and recombination operators play a key role in determining the speed and quality of Genetic and Evolutionary Algorithms (GEAs). Prior work has analyzed the effects of these operators on genotypic variation, ofte…
Evolutionary AlgorithmsProvably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning
Meta-learning for offline reinforcement learning (OMRL) is an understudied problem with tremendous potential impact by enabling RL algorithms in many real-world applications. A popular solution to the problem is to infer…
Contrastive LearningMeta-Learningreinforcement-learningReinforcement Learning (RL)+1Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
In view of its power in extracting feature representation, contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning (RL), leading to efficient policy learni…
Contrastive LearningDeep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)+2Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm
Unexpected stimuli induce "error" or "surprise" signals in the brain. The theory of predictive coding promises to explain these observations in terms of Bayesian inference by suggesting that the cortex implements variati…
Bayesian InferenceVariational InferenceLearning One Representation to Optimize All Rewards
We introduce the forward-backward (FB) representation of the dynamics of a reward-free Markov decision process. It provides explicit near-optimal policies for any reward specified a posteriori. During an unsupervised pha…
All