Skip to Main content Skip to Navigation
Conference papers

UCB Momentum Q-learning: Correcting the bias without forgetting

Pierre Ménard 1 Omar Darwiche Domingues 2 Xuedong Shang 2 Michal Valko 3 
2 Scool - Scool
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : We propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new algorithm for reinforcement learning in tabular and possibly stagedependent, episodic Markov decision process. UCBMQ is based on Q-learning where we add a momentum term and rely on the principle of optimism in face of uncertainty to deal with exploration. Our new technical ingredient of UCBMQ is the use of momentum to correct the bias that Q-learning suffers while, at the same time, limiting the impact it has on the the second-order term of the regret. For UCBMQ, we are able to guarantee a regret of at most O(√ H 3 SAT + H 4 SA) where H is the length of an episode, S the number of states, A the number of actions, T the number of episodes and ignoring terms in poly log(SAHT). Notably, UCBMQ is the first algorithm that simultaneously matches the lower bound of Ω(√ H 3 SAT) for large enough T and has a second-order term (with respect to the horizon T) that scales only linearly with the number of states S.
Document type :
Conference papers
Complete list of metadata
Contributor : Michal Valko Connect in order to contact the contributor
Submitted on : Friday, July 16, 2021 - 4:08:47 PM
Last modification on : Tuesday, June 14, 2022 - 11:58:48 AM
Long-term archiving on: : Sunday, October 17, 2021 - 7:06:16 PM


Files produced by the author(s)


  • HAL Id : hal-03289033, version 1



Pierre Ménard, Omar Darwiche Domingues, Xuedong Shang, Michal Valko. UCB Momentum Q-learning: Correcting the bias without forgetting. International Conference on Machine Learning, Jul 2021, Vienna / Virtual, Austria. ⟨hal-03289033⟩



Record views


Files downloads