Meta-Learning Parameterized Skills
We propose a novel parameterized skill-learning algorithm that aims to learn transferable parameterized skills and synthesize them into a new action space that supports efficient learning in long-horizon tasks. We propose to leverage off-policy Meta-RL combined with a trajectory-centric smoothness term to learn a set of parameterized skills. Our agent can use these learned skills to construct a three-level hierarchical framework that models a Temporally-extended Parameterized Action Markov Decision Process. We empirically demonstrate that the proposed algorithms enable an agent to solve a set of difficult long-horizon (obstacle-course and robot manipulation) tasks.
Code (1)
Tasks
Meta-LearningRobot ManipulationSimilar Papers 제목 키워드 기반
Learning Parameterized Skills from Demonstrations
We present DEPS, an end-to-end algorithm for discovering parameterized skills from expert demonstrations. Our method learns parameterized skill policies jointly with a meta-policy that selects the appropriate discrete sk…
Understanding Benign Overfitting in Gradient-Based Meta Learning
Meta learning has demonstrated tremendous success in few-shot learning with limited supervised data. In those settings, the meta model is usually overparameterized. While the conventional statistical learning theory sugg…
Few-Shot LearningLearning TheoryMeta-LearningWebXSkill: Skill Learning for Autonomous Web Agents
Autonomous web agents powered by large language models (LLMs) remain brittle on long-horizon browser workflows. A key bottleneck is a grounding gap in existing skill formulations: textual workflow skills provide natural …
Provable Generalization of Overparameterized Meta-learning Trained with SGD
Despite the superior empirical success of deep meta-learning, theoretical understanding of overparameterized meta-learning is still limited. This paper studies the generalization of a widely used meta-learning approach, …
Generalization BoundsMeta-LearningLearning Deep Parameterized Skills from Demonstration for Re-targetable Visuomotor Control
Robots need to learn skills that can not only generalize across similar problems but also be directed to a specific goal. Previous methods either train a new skill for every different goal or do not infer the specific ta…