Search Results for author:
Found 4 papers, 0 papers with code
Truly No-Regret Learning in Constrained MDPs
As Efroni et al. (2020) pointed out, it is an open question whether primal-dual algorithms can provably achieve sublinear regret if we do not allow error cancellations.
Provably Learning Nash Policies in Constrained Markov Potential Games
Multi-agent reinforcement learning (MARL) addresses sequential decision-making problems with multiple agents, where each agent optimizes its own objective.
Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes
Unlike existing Lagrangian approaches, our algorithm achieves this regret without the need for the cancellation of errors.
Multi-Player Bandits: The Adversarial Case
We consider a setting where multiple players sequentially choose among a common set of actions (arms).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
