Model-based Adversarial Imitation Learning from Demonstrations and Human Reward
Jie Huang,Jiangshan Hao,Rongshun Juan,Randy Gomez,Keisuke Nakarnura,Guangliang Li,Jie Huang,Jiangshan Hao,Rongshun Juan,Randy Gomez,Keisuke Nakarnura,Guangliang Li
Reinforcement learning (RL) can potentially be applied to real-world robot control in complex and uncertain environments. However, it is difficult or even unpractical to design an efficient reward function for various tasks, especially those large and high-dimensional environments. Generative adversarial imitation learning (GAIL) - a general model-free imitation learning method, allows robots to d...
