Computationally Efficient RL Under Linear Bellman Completeness For Deterministic Dynamics

Abstract

We study computationally and statistically efficient Reinforcement Learning algorithms for the linear Bellman Complete setting. This setting uses linear function approximation to capture value functions and unifies existing models like linear Markov Decision Processes (MDP) and Linear Quadratic Regulators (LQR). While it is known from the prior works that this setting is statistically tractable, it remained open whether a computationally efficient algorithm exists. Our work provides a computationally efficient algorithm for the linear Bellman complete setting that works for MDPs with large action spaces, random initial states, and random rewards but relies on the underlying dynamics to be deterministic. Our approach is based on randomization: we inject random noise into least squares regression problems to perform optimistic value iteration. Our key technical contribution is to carefully design the noise to only act in the null space of the training data to ensure optimism while circum

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywu2024computationally

Related papers

• Nonstationary Reinforcement Learning With Linear Function Approximation (2020)0.00
• Nearly Minimax Optimal Reinforcement Learning For Linear Markov Decision Processes (2022)0.00
• Taming "data-hungry" Reinforcement Learning? Stability In Continuous State-action Spaces (2024)2.26
• Sample-efficient Reinforcement Learning Is Feasible For Linearly Realizable Mdps With Limited Revisiting (2021)0.00
• Distributionally Robust Off-dynamics Reinforcement Learning: Provable Efficiency With Linear Function Approximation (2024)0.00
• Sample Complexity Of The Linear Quadratic Regulator: A Reinforcement Learning Lens (2024)0.00
• Provably Efficient Model-free RL In Leader-follower MDP With Linear Function Approximation (2022)0.00
• Minimax Optimal And Computationally Efficient Algorithms For Distributionally Robust Offline Reinforcement Learning (2024)0.00