Reward-Relevance-Filtered Linear Offline Reinforcement Learning
This paper studies offline reinforcement learning with linear function approximation in a setting with decision-theoretic, but not estimation sparsity. The structural restrictions of the data-generating process presume that the transitions factor into a sparse component that affects the reward and could affect additional exogenous dynamics that do not affect the reward. Although the minimally sufficient adjustment set for estimation of full-state transition properties depends on the whole state, the optimal policy and therefore state-action value function depends only on the sparse component: we call this causal/decision-theoretic sparsity. We develop a method for reward-filtering the estimation of the state-action value function to the sparse component by a modification of thresholded lasso in least-squares policy evaluation. We provide theoretical guarantees for our reward-filtered linear fitted-Q-iteration, with sample complexity depending only on the size of the sparse component.
Code (0)
등록된 구현이 없습니다.
Tasks
reinforcement-learningReinforcement LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?
In recent years, extensive work has explored the application of the Transformer architecture to reinforcement learning problems. Among these, Decision Transformer (DT) has gained particular attention in the context of of…
Reinforcement LearningOffline RLNonlinear Inverse Reinforcement Learning with Gaussian Processes
We present a probabilistic algorithm for nonlinear inverse reinforcement learning. The goal of inverse reinforcement learning is to learn the reward function in a Markov decision process from expert demonstrations. While…
Gaussian Processesreinforcement-learningReinforcement LearningReinforcement Learning (RL)A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs
We study offline reinforcement learning (RL) with linear MDPs under the infinite-horizon discounted setting which aims to learn a policy that maximizes the expected discounted cumulative reward using a pre-collected data…
Offline RLReinforcement Learning (RL)The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning
Self-supervised methods have become crucial for advancing deep learning by leveraging data itself to reduce the need for expensive annotations. However, the question of how to conduct self-supervised offline reinforcemen…
Offline RLreinforcement-learningReinforcement Learning (RL)TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user exper…
Reinforcement Learning