31 citations · 74 across the 9 of their papers we have counts for
8 papers · 1 filter
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…
Adaptive Multi-Goal Exploration
Jean Tarbouriech, Omar Darwiche Domingues, Pierre Ménard +3
We introduce a generic strategy for provably efficient multi-goal exploration. It relies on AdaGoal, a novel goal selection scheme that leverages a measure of uncertainty in reachi…
Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited
Omar Darwiche Domingues, Pierre Ménard, Emilie Kaufmann +1
In this paper, we propose new problem-independent lower bounds on the sample complexity and regret in episodic MDPs, with a particular focus on the non-stationary case in which the…
Fast active learning for pure exploration in reinforcement learning
Pierre Ménard, Omar Darwiche Domingues, Anders Jonsson +3
Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the…
A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces
Omar Darwiche Domingues, Pierre Ménard, Matteo Pirotta +2
In this work, we propose KeRNS: an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes (MDPs) whose state-action set is endowed with a metric.…
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
Anders Jonsson, Emilie Kaufmann, Pierre Ménard +3
We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for planning in a Markov Decision Process in which transitions have a finite support. We prove an uppe…
Adaptive Reward-Free Exploration
Emilie Kaufmann, Pierre Ménard, Omar Darwiche Domingues +3
Reward-free exploration is a reinforcement learning setting studied by Jin et al. (2020), who address it by running several algorithms with regret guarantees in parallel. In our wo…
Kernel-Based Reinforcement Learning: A Finite-Time Analysis
Omar Darwiche Domingues, Pierre Ménard, Matteo Pirotta +2
We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning problems whose state-action space is endowed with a metric. We introduce Kernel-UCBVI, a m…