Songtao Feng

multitask learning (2) reinforcement learning (2) reward-free learning (2) representation learning (2) online learning (1) transfer learning (1) function approximation (1) primal-dual optimization (1) constrained optimization (1) dynamic regret (1) nash equilibrium (1) downstream task (1) markov game (1) multitask representation learning (1) low-rank model (1) low-rank mdp (1) reward-free exploration (1) sliding window (1) potential game (1) markov potential game (1)