W Li, X Wang, B Jin, H Zha - International Conference on …, 2023 - proceedings.mlr.press
Offline reinforcement learning typically introduces a hierarchical structure to solve the long- horizon problem so as to address its thorny issue of variance accumulation. Problems of …
Learning contact-rich manipulation skills is essential. Such skills require the robots to interact with the environment with feasible manipulation trajectories and suitable compliance …
Deep generative models (DGMs) have demonstrated great success across various domains, particularly in generating texts, images, and videos using models trained from offline data …
Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in …
Developing agents that can execute multiple skills by learning from pre-collected datasets is an important problem in robotics, where online interaction with the environment is extremely …
Autonomous driving (AD) holds the potential to revolutionize transportation efficiency, but its success hinges on robust behavior planning (BP) mechanisms. Reinforcement learning (RL) …
The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve complex tasks effectively. However, learning the models for both low and high-level …
H Yuan, Z Mu, F Xie, Z Lu - The Twelfth International Conference on …, 2024 - openreview.net
Pre-training on task-agnostic large datasets is a promising approach for enhancing the sample efficiency of reinforcement learning (RL) in solving complex tasks. We present …
Z Li, F Nie, Q Sun, F Da, H Zhao - arXiv preprint arXiv:2309.13614, 2023 - arxiv.org
Learning-based vehicle planning is receiving increasing attention with the emergence of diverse driving simulators and large-scale driving datasets. While offline reinforcement …