← Search

Jiangshan Hao

2 accepted papers

2023

GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback

ICRA 2023poster

Generative adversarial imitation learning (GAIL) — a general model-free imitation learning method, allows robots to directly learn policies from expert trajectories in large environments. However, GAIL shares the limitation of other imitation learning methods that they can seldom surpass the perform…

Cited by 10SourceScholar
2023

Model-based Adversarial Imitation Learning from Demonstrations and Human Reward

IROS 2023poster

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 advers…

Cited by 1SourceScholar