Обучение с подкреплением с инверсией противника
method
ID: inverseadversarialreinforcementlearning
Related Papers
Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management
AbstractFor task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL. To …...