Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative

no code implementations • 13 Jul 2023 • Sho Shimoyama, Tetsuro Morimura, Kenshi Abe, Toda Takamichi, Yuta Tomomatsu, Masakazu Sugiyama, Asahi Hentona, Yuuki Azuma, Hirotaka Ninomiya

One way to estimate rewards from collected data is to train the reward estimator and dialog policy simultaneously using adversarial learning (AL).

Reinforcement Learning (RL)