Results show that aligning planner-generated demonstrations with the pretraining distribution can make TAMP an effective source of data for VLA fine-tuning, and incorporate the pretraining distribution directly into TAMP trajectory generation.
Samrat Sahoo, Yi-Xuan Huang, Tom Silver· 1 citation· ⚡1
TANDEM (Tamp with As-Needed Demonstrations for Efficient Model fine-tuning), a system that combines TAMP with selective human teleoperation to collect demonstrations for tasks beyond the planner's capabilities, is presented.
Samrat Sahoo, Li Ji, Tom Silver et al.· 0 citations
EMPIRIC, an agent that learns a residual world model: a physics engine extended with code for the missing mechanisms, that learns interpretable, reusable models, and solves more tasks with fewer environment interactions than all three baselines.
Yi-Chao Liang, Amber Li, Dat Nguyen et al.· arXiv.org· 1 citation
This work finds that coding agents are surprisingly effective at generalized TAMP: all three agent configurations outperform hand-engineered planners, one-shot generation, and an LLM-based generalized planning baseline in mean success.
Matteo Merler, Bo-Wen Li, Josh Roy et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.