A survey of learning‐based robot motion planning

J Wang, T Zhang, N Ma, Z Li, H Ma… - IET Cyber‐Systems …, 2021 - Wiley Online Library
A fundamental task in robotics is to plan collision‐free motions among a set of obstacles.
Recently, learning‐based motion‐planning methods have shown significant advantages in …

Decision s4: Efficient sequence-based rl via state spaces layers

S Bar-David, I Zimerman, E Nachmani… - arXiv preprint arXiv …, 2023 - arxiv.org
Recently, sequence learning methods have been applied to the problem of off-policy
Reinforcement Learning, including the seminal work on Decision Transformers, which …

Measuring and predicting variation in the interestingness of physical structures

C Holdaway, DM Bear, SF Radwan… - Proceedings of the …, 2021 - escholarship.org
Curiosity drives much of human behavior, but its open-ended nature makes it hard to study
in the laboratory. Moreover, computational theories of curiosity--models of how intrinsic …

[HTML][HTML] Automatic extension of a symbolic mobile manipulation skill set

J Förster, L Ott, J Nieto, N Lawrance, R Siegwart… - Robotics and …, 2023 - Elsevier
Symbolic planning can provide an intuitive interface for non-expert users to operate
autonomous robots by abstracting away much of the low-level programming. However …

[PDF][PDF] Learning to Plan with Optimistic Action Models

C Moses, LP Kaelbling, T Lozano-Pérez - people.csail.mit.edu
Planning for and successfully executing manipulation tasks require accurate dynamics
models. Existing methods for engineering these models often fail to capture the underlying …