6 papers
LEACL: LLM-Enhanced Automatic Curriculum Learning for Reinforcement Learning in Long-Horizon Manipulation Tasks
Faraz Heravi, James Ouyang, Zifan Xu +3
Long-horizon manipulation tasks pose significant challenges for reinforcement learning due to sparse reward signals and long horizons. Automatic curriculum learning (ACL) has been…
Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
Jiaheng Hu, Jay Shim, Chen Tang +4
Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving…
Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning
Yoonwoo Kim, Raghav Arora, Roberto MartÃn-MartÃn +3
Robot planning in partially observable environments, where not all objects are known or visible, is a challenging problem, as it requires reasoning under uncertainty through partia…
ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork
Caroline Wang, Arrasy Rahman, Jiaxun Cui +2
Learning to collaborate with previously unseen partners is a fundamental generalization challenge in multi-agent learning, known as Ad Hoc Teamwork (AHT). Existing AHT approaches o…
PRESTO: Fast Motion Planning Using Diffusion Models Based on Key-Configuration Environment Representation
Mingyo Seo, Yoonyoung Cho, Yoonchang Sung +3
We introduce a learning-guided motion planning framework that generates seed trajectories using a diffusion model for trajectory optimization. Given a workspace, our method approxi…
Effort Allocation for Deadline-Aware Task and Motion Planning: A Metareasoning Approach
Yoonchang Sung, Shahaf S. Shperberg, Qi Wang +1
In robot planning, tasks can often be achieved through multiple options, each consisting of several actions. This work specifically addresses deadline constraints in task and motio…