Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies

Neural Information Processing Systems (NeurIPS)


State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing full-planning on Markov Decision Processes (MDPs) built by the gathered experience. In this paper, we focus on model-based RL in the finite-state finite-horizon undiscounted MDP setting and establish that exploring with greedy policies – act by 1-step planning – can achieve tight minimax performance in terms of regret, Õ(√HSAT). Thus, full-planning in model-based RL can be avoided altogether without any performance degradation, and, by doing so, the computational complexity decreases by a factor of S. The results are based on a novel analysis of real-time dynamic programming, then extended to model-based RL. Specifically, we generalize existing algorithms that perform full-planning to act by 1-step planning. For these generalizations, we prove regret bounds with the same rate as their full-planning counterparts.

Related Publications

All Publications

LEEP: A New Measure to Evaluate Transferability of Learned Representations

Cuong V. Nguyen, Tal Hassner, Matthias Seeger, Cedric Archambeau

ICML - July 13, 2020

The Differentiable Cross-Entropy Method

Brandon Amos, Denis Yarats

ICML - July 12, 2020

Growing Action Spaces

Gregory Farquhar, Laura Gustafson, Zeming Lin, Shimon Whiteson, Nicolas Usunier, Gabriel Synnaeve

July 14, 2020

Stochastic Hamiltonian Gradient Methods for Smooth Games

Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau, Pascal Vincent, Simon Lacoste-Julien, Ioannis Mitliagkas

ICML - July 12, 2020

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy