Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation

Abstract

We propose an algorithm that uses linear function approximation (LFA) for stochastic shortest path (SSP). Under minimal assumptions, it obtains sublinear regret, is computationally efficient, and uses stationary policies. To our knowledge, this is the first such algorithm in the LFA literature (for SSP or other formulations). Our algorithm is a special case of a more general one, which achieves regret square root in the number of episodes given access to a certain computation oracle.

This version removes most assumptions of the prior one

References in corpus (10)

• Provably Efficient Reinforcement Learning with Linear Function Approximation
• Learning Near Optimal Policies with Low Inherent Bellman Error
• Optimism in Reinforcement Learning with Generalized Linear Function Approximation
• Logarithmic Regret for Reinforcement Learning with Linear Function Approximation
• An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap
• Online Learning for Stochastic Shortest Path Model via Posterior Sampling
• Minimax Regret for Stochastic Shortest Path
• Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret
• Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path
• Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

Cited by in corpus (4)

• A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes
• A Provably Efficient Sample Collection Strategy for Reinforcement Learning
• Learning Stochastic Shortest Path with Linear Function Approximation
• Adaptive Multi-Goal Exploration