RT-H learns robot policies by first predicting language motions as an intermediate representation and then mapping those plus the high-level task to actions, yielding more robust multi-task performance and the ability to learn from language interventions.
Interactive language: Talking to robots in real time
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
SuperIgor uses iterative co-training of a language model planner and a goal-conditional RL agent to self-generate and refine plans, resulting in stricter instruction adherence and better generalization to unseen instructions.
citing papers explorer
-
RT-H: Action Hierarchies Using Language
RT-H learns robot policies by first predicting language motions as an intermediate representation and then mapping those plus the high-level task to actions, yielding more robust multi-task performance and the ability to learn from language interventions.
-
Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning
SuperIgor uses iterative co-training of a language model planner and a goal-conditional RL agent to self-generate and refine plans, resulting in stricter instruction adherence and better generalization to unseen instructions.