Mehdi Jafarnia Jahromi

regret bound (4) posterior sampling (2) online learning (2) reinforcement learning (2) partially observable markov decision process (1) multi-agent learning (1) linear function approximation (1) stochastic game (1) average reward (1) model-free reinforcement learning (1) adversarial bandit (1) average-reward mdp (1) bayesian regret bound (1) zero-sum stochastic game (1) average-reward criterion (1) multi-agent system (1) infinite horizon (1) infinite-horizon average-reward (1) bayesian learning (1) natural policy gradient (1)