Provably Efficient Ucb-type Algorithms For Learning Predictive State Representations

Abstract

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 tot

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuang2023provably

Related papers

• Provable Representation With Efficient Planning For Partial Observable Reinforcement Learning (2023)0.00
• Robust Anytime Learning Of Markov Decision Processes (2022)0.00
• Bridging State And History Representations: Understanding Self-predictive RL (2024)0.00
• Embed To Control Partially Observed Systems: Representation Learning With Provable Sample Efficiency (2022)0.00
• Optimal Decision-making In Mixed-agent Partially Observable Stochastic Environments Via Reinforcement Learning (2019)0.00
• Provably Efficient Reinforcement Learning In Partially Observable Dynamical Systems (2022)0.00
• GEC: A Unified Framework For Interactive Decision Making In MDP, POMDP, And Beyond (2022)0.00
• Near-optimal Partially Observable Reinforcement Learning With Partial Online State Information (2023)0.00