4 citations · 11 across the 4 of their papers we have counts for
4 papers
Learning from Active Human Involvement through Proxy Value Propagation
Zhenghao Peng, Wenjie Mo, Chenda Duan +2
Learning from active human involvement enables the human subject to actively intervene and demonstrate to the AI agent during training. The interaction and corrective feedback from…
Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response
Junfeng Long, Zirui Wang, Quanyi Li +3
Robust locomotion control depends on accurate state estimations. However, the sensors of most legged robots can only provide partial and noisy observations, making the estimation p…
CAT: Closed-loop Adversarial Training for Safe End-to-End Driving
Linrui Zhang, Zhenghao Peng, Quanyi Li +1
Driving safety is a top priority for autonomous vehicles. Orthogonal to prior work handling accident-prone traffic events by algorithm designs at the policy level, we investigate a…
Guarded Policy Optimization with Imperfect Online Demonstrations
Zhenghai Xue, Zhenghao Peng, Quanyi Li +2
The Teacher-Student Framework (TSF) is a reinforcement learning setting where a teacher agent guards the training of a student agent by intervening and providing online demonstrati…