Botao Hao

regret bound (8) bayesian regret (3) linear function approximation (3) linear bandit (3) online learning (3) multi-armed bandit (3) reinforcement learning (3) sample efficiency (3) neural network (2) information-directed sampling (2) off-policy evaluation (2) sparse learning (2) markov decision process (2) fitted q-evaluation (2) nonparametric regression (2) thompson sampling (2) contextual bandit (2) policy iteration (2) expectation maximization (1) sequential decision making (1)