Search Results for author:
Found 2 papers, 0 papers with code
Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses in the bandit feedback setting.
Dynamic Regret of Online Markov Decision Processes
For these three models, we propose novel online ensemble algorithms and establish their dynamic regret guarantees respectively, in which the results for episodic (loop-free) SSP are provably minimax optimal in terms of time horizon and certain non-stationarity measure.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
