作者: Oliver Lemon , Simon Keizer , Heriberto Cuayáhuitl
DOI:
关键词: Reinforcement learning 、 Negotiation 、 Computer science 、 Supervised learning 、 Situated 、 Intelligent agent 、 State space 、 Dialogue management 、 Natural (music) 、 Human–computer interaction
摘要: … In summary, strategic dialogue agents trained with deep reinforcement learning have the potential to acquire highly competitive behaviour, not just from training against strong …