Mohammad Gheshlaghi azar

reinforcement learning (6) self-supervised learning (4) representation learning (3) policy optimization (2) contrastive learning (2) latent representation (2) policy iteration (2) markov decision process (2) mirror descent (2) policy gradient (2) dynamic programming (2) transfer learning (2) direct preference optimization (1) online learning (1) preference learning (1) function approximation (1) reward modeling (1) policy learning (1) game theory (1) minimax optimality (1)