robosuite
PulseAugur coverage of robosuite — every cluster mentioning robosuite across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Guide to Imitation Learning for Robotics Released
This article provides a guide to implementing imitation learning (IL) for robotics, focusing on vision-based policies trained from scratch. It contrasts IL with classic explicit policies and reinforcement learning, high…
-
Robots learn skills through play, boosting task performance
Researchers have introduced Playful Agentic Robot Learning (RATs), a system where embodied agents learn skills through self-directed play before tackling specific tasks. This approach allows agents to propose novel expl…
-
New COMET Algorithm Enhances AI Planning with Object-Centric Approach
Researchers have introduced COMET, a novel model-based reinforcement learning algorithm designed for planning. COMET utilizes Monte Carlo Tree Search within a slot-structured latent space, pairing a frozen unsupervised …
-
Robotics AI uses atomic probes to govern skill updates in compositional policies
Researchers have developed a new method called Atomic-Probe Governance to manage skill updates in compositional robot policies. This approach addresses the challenge of how changes in individual skills affect the overal…