Nantas Nardelli

deep reinforcement learning (1) representation learning (1) multi-agent reinforcement learning (1) reinforcement learning (1) imitation learning (1) transfer learning (1) instruction following (1) natural language understanding (1) multitask learning (1) deep learning (1) hierarchical reinforcement learning (1) importance sampling (1) value function (1) sequential decision (1) reward function (1) natural language (1) experience replay (1) deep q-learning (1) textual domain knowledge (1) option learning (1)