-
Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited
In this paper, we propose new problem-independent lower bounds on the sa...
10/07/2020 ∙ by Omar Darwiche Domingues, et al. ∙
0
∙
share
read it
-
Fast active learning for pure exploration in reinforcement learning
Realistic environments often provide agents with very limited feedback. ...
07/27/2020 ∙ by Pierre Ménard, et al. ∙
10
∙
share
read it
-
A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces
In this work, we propose KeRNS: an algorithm for episodic reinforcement ...
07/09/2020 ∙ by Omar Darwiche Domingues, et al. ∙
51
∙
share
read it
-
Adaptive Reward-Free Exploration
Reward-free exploration is a reinforcement learning setting recently stu...
06/11/2020 ∙ by Emilie Kaufmann, et al. ∙
3
∙
share
read it
-
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algo...
06/10/2020 ∙ by Anders Jonsson, et al. ∙
10
∙
share
read it
-
Regret Bounds for Kernel-Based Reinforcement Learning
We consider the exploration-exploitation dilemma in finite-horizon reinf...
04/12/2020 ∙ by Omar Darwiche Domingues, et al. ∙
0
∙
share
read it
