Reward-Relevance-Filtered Linear Offline Reinforcement Learning
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jan-23-2024
- Country:
- Europe > Spain (0.04)
- North America > United States
- California (0.14)
- Genre:
- Research Report (1.00)
- Industry:
- Health & Medicine (0.46)
- Technology: