Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes
Policy Optimization (PO) methods are among the most popular Reinforcement Learning (RL) algorithms in practice. Recently, Sherman et al. [2023a] proposed a PO-based algorithm with rate-optimal regret guarantees under the linear Markov Decision Process (MDP) model. However, their algorithm relies on a costly pure exploration warm-up phase that is hard to implement in practice. This paper eliminates this undesired warm-up phase, replacing it with a simple and efficient contraction mechanism. Our PO algorithm achieves rate-optimal regret with improved dependence on the other parameters of the problem (horizon and function approximation dimension) in two fundamental settings: adversarial losses with full-information feedback and stochastic losses with bandit feedback.
Jul-3-2024
- Country:
- North America
- United States
- Nevada (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California > San Mateo County
- Menlo Park (0.04)
- Canada > British Columbia
- United States
- Asia > Middle East
- Jordan (0.04)
- Israel > Tel Aviv District
- Tel Aviv (0.04)
- North America
- Genre:
- Research Report (0.64)