Michita Imai

deep reinforcement learning (1) offline reinforcement learning (1) natural language processing (1) self-supervised learning (1) question generation (1) off-policy learning (1) deep rl (1) visual dialogue (1) goal-oriented dialogue (1) offline rl (1) dialogue understanding (1) offline deep reinforcement learning (1) communication breakdown (1) descriptive question (1) interpretive nonsense (1)