Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Near-Optimal Regret for Semi-Bandit Learning of Monotone Stochastic Problems
Zhengjia Zhuo, Viswanath Nagarajan
We consider the task of learning an (approximately) optimal policy for stochastic optimization problems where the true distributions are unknown. In each period, the algorithm play…
cs.LG2026
Learning Markov Decision Processes under Fully Bandit Feedback
Zhengjia Zhuo, Anupam Gupta, Viswanath Nagarajan
A standard assumption in Reinforcement Learning is that the agent observes every visited state-action pair in the associated Markov Decision Process (MDP), along with the per-step…