Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Woo, Honguk"'
Continual Imitation Learning (CiL) involves extracting and accumulating task knowledge from demonstrations across multiple stages and tasks to achieve a multi-task policy. With recent advancements in foundation models, there has been a growing intere
Externí odkaz:
http://arxiv.org/abs/2410.22658
Reinforcement learning (RL) with diverse offline datasets can have the advantage of leveraging the relation of multiple tasks and the common skills learned across those tasks, hence allowing us to deal with real-world complex problems efficiently in
Externí odkaz:
http://arxiv.org/abs/2408.15593
Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches rarely consider learning Pareto-optimal policies from a limited pool of
Externí odkaz:
http://arxiv.org/abs/2408.12110
Goal-conditioned (GC) policy learning often faces a challenge arising from the sparsity of rewards, when confronting long-horizon goals. To address the challenge, we explore skill-based GC policy learning in offline settings, where skills are acquire
Externí odkaz:
http://arxiv.org/abs/2408.11300
In embodied instruction-following (EIF), the integration of pretrained language models (LMs) as task planners emerges as a significant branch, where tasks are planned at the skill level by prompting LMs with pretrained skills and user instructions. H
Externí odkaz:
http://arxiv.org/abs/2408.01024
When adopting a deep learning model for embodied agents, it is required that the model structure be optimized for specific tasks and operational conditions. Such optimization can be static such as model compression or dynamic such as adaptive inferen
Externí odkaz:
http://arxiv.org/abs/2406.11128
Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task-agnostically from offline datasets, can accelerate the policy learnin
Externí odkaz:
http://arxiv.org/abs/2403.00225
One-shot imitation is to learn a new task from a single demonstration, yet it is a challenging problem to adopt it for complex tasks with the high domain diversity inherent in a non-stationary environment. To tackle the problem, we explore the compos
Externí odkaz:
http://arxiv.org/abs/2402.08369
This work explores the zero-shot adaptation capability of semantic skills, semantically interpretable experts' behavior patterns, in cross-domain settings, where a user input in interleaved multi-modal snippets can prompt a new long-horizon task for
Externí odkaz:
http://arxiv.org/abs/2402.07418
Recently, deep reinforcement learning (RL) has proven its feasibility in solving combinatorial optimization problems (COPs). The learning-to-rank techniques have been studied in the field of information retrieval. While several COPs can be formulated
Externí odkaz:
http://arxiv.org/abs/2201.00695