6 papers
A single algorithm for both restless and rested rotting bandits
Julien Seznec, Pierre Ménard, Alessandro Lazaric +1
In many application domains (e.g., recommender systems, intelligent tutoring systems), the rewards associated to the actions tend to decrease over time. This decay is either caused…
Planning in entropy-regularized Markov decision processes and games
Jean-Bastien Grill, Omar Darwiche Domingues, Pierre Ménard +2
We propose SmoothCruiser, a new planning algorithm for estimating the value function in entropy-regularized Markov decision processes and two-player games, given a generative model…
The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
Côme Fiegel, Pierre Ménard, Tadashi Kozuno +2
We study the problem of learning in zero-sum matrix games with repeated play and bandit feedback. Specifically, we focus on developing uncoupled algorithms that guarantee, without…
Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier
Come Fiegel, Pierre Menard, Tadashi Kozuno +2
We study the problem of learning minimax policies in zero-sum matrix games. Fiegel et al. (2025) recently showed that achieving last-iterate convergence in this setting is harder w…
Proximal Point Nash Learning from Human Feedback
Daniil Tiapkin, Daniele Calandriello, Denis Belomestny +5
Traditional Reinforcement Learning from Human Feedback (RLHF) often relies on reward models, frequently assuming preference structures like the Bradley--Terry model, which may not…
Model-free Posterior Sampling via Learning Rate Randomization
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello +6
In this paper, we introduce Randomized Q-learning (RandQL), a novel randomized model-free algorithm for regret minimization in episodic Markov Decision Processes (MDPs). To the bes…