Keith Ross

deep reinforcement learning (3) sample efficiency (2) offline reinforcement learning (1) imitation learning (1) machine translation (1) policy learning (1) arabic dialect (1) constrained optimization (1) value function (1) continuous control (1) batch reinforcement learning (1) entropy maximization (1) off-policy learning (1) visual representation learning (1) safe reinforcement learning (1) low-resource language (1) replay buffer (1) offline rl (1) cost constraint (1) small language model (1)