4 papers · 1 filter
Ego-centric Learning of Communicative World Models for Autonomous Driving
Hang Wang, Dechen Gao, Junshan Zhang
We study multi-agent reinforcement learning (MARL) for tasks in complex high-dimensional environments, such as autonomous driving. MARL is known to suffer from the \textit{partial…
IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning
Dechen Gao, Hang Wang, Hanchu Zhou +5
Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promote…
AdaWM: Adaptive World Model based Planning for Autonomous Driving
Hang Wang, Xin Ye, Feng Tao +5
World model based reinforcement learning (RL) has emerged as a promising approach for autonomous driving, which learns a latent dynamics model and uses it to train a planning polic…
CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving
Dechen Gao, Shuangyu Cai, Hanchu Zhou +3
To safely navigate intricate real-world scenarios, autonomous vehicles must be able to adapt to diverse road conditions and anticipate future events. World model (WM) based reinfor…