Roberta Raileanu

reinforcement learning (5) value function (4) large language model (4) exploration bonus (3) game theory (2) deep reinforcement learning (2) tool use (2) language model (2) text generation (2) representation learning (2) sample efficiency (1) domain generalization (1) transfer learning (1) policy optimization (1) zero-shot learning (1) imitation learning (1) self-supervised learning (1) few-shot learning (1) sequential decision making (1) epistemic uncertainty (1)