相关论文: LEAGUE: Guided Skill Learning and Abstraction for …

Reinforcement learning can train policies that effectively perform complex tasks. However for long-horizon tasks, the performance of these methods degrades with horizon, often necessitating reasoning over and chaining lower-level skills.…

Domain models enable autonomous agents to solve long-horizon tasks by producing interpretable plans. However, in open-world environments, a single general domain model cannot capture the variety of tasks, so agents must generate suitable…

We describe a framework for using natural language to design state abstractions for imitation learning. Generalizable policy learning in high-dimensional observation spaces is facilitated by well-designed state representations, which can…

Achieving coordinated teamwork among legged robots requires both fine-grained locomotion control and long-horizon strategic decision-making. Robot soccer offers a compelling testbed for this challenge, combining dynamic, competitive, and…

Open-ended learning benefits immensely from the use of symbolic methods for goal representation as they offer ways to structure knowledge for efficient and transferable learning. However, the existing Hierarchical Reinforcement Learning…

Developing general robotic systems capable of manipulating in unstructured environments is a significant challenge, particularly as the tasks involved are typically long-horizon and rich-contact, requiring efficient skill transfer across…

Recent advancements in large language models (LLMs) have enabled their use as agents for planning complex tasks. Existing methods typically rely on a thought-action-observation (TAO) process to enhance LLM performance, but these approaches…

Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…

We consider the challenging problem of using domain knowledge to improve deep reinforcement learning policies. To this end, we propose LEGIBLE, a novel approach, following a multi-step process, which starts by mining rules from a deep RL…

Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, a precise characterization…

Everyday tasks of long-horizon and comprising a sequence of multiple implicit subtasks still impose a major challenge in offline robot control. While a number of prior methods aimed to address this setting with variants of imitation and…

Human-robot cooperation is essential in environments such as warehouses and retail stores, where workers frequently handle deformable objects like paper, bags, and fabrics. Coordinating robotic actions with human assistance remains…

Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…

Learning goal conditioned control in the real world is a challenging open problem in robotics. Reinforcement learning systems have the potential to learn autonomously via trial-and-error, but in practice the costs of manual reward design,…

In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals. Specifically, traditional symbolic planners fail to generate plans when the robot's planning…

Assembling a slave object into a fixture-free master object represents a critical challenge in flexible manufacturing. Existing deep reinforcement learning-based methods, while benefiting from visual or operational priors, often struggle…

Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving…

Adapting to unforeseen novelties in open-world environments remains a major challenge for autonomous systems. While hybrid planning and reinforcement learning (RL) approaches show promise, they often suffer from sample inefficiency, slow…

Generative adversarial imitation learning (GAIL) has attracted increasing attention in the field of robot learning. It enables robots to learn a policy to achieve a task demonstrated by an expert while simultaneously estimating the reward…

Solving robotic navigation tasks via reinforcement learning (RL) is challenging due to their sparse reward and long decision horizon nature. However, in many navigation tasks, high-level (HL) task representations, like a rough floor plan,…