EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
[Sztuczna inteligencja] Autorzy: Python Song, Zhixuan Liang, Kelsey Fu i 3 więcej
Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt around the model, but current self-evolving harnesses use robot trials inefficiently when deciding which code and skill changes to pursue. We introduce EmbodiedRSI, a self-evolving agentic harness that autonomously decides where to explore next and turns the resulting physical interaction into improved code and skills. EmbodiedRSI realizes this through a Fast-Slow Dual-System Architecture, in which competing code and skill hypotheses are maintained in a Hypothesis Graph. Value-of-Information Experiment Selection chooses physical experiments that can distinguish these hypothe…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja