相关论文: Learning Functionally Decomposed Hierarchies for C…

Reinforcement learning (RL), while often powerful, can suffer from slow learning speeds, particularly in high dimensional spaces. The autonomous decomposition of tasks and use of hierarchical methods hold the potential to significantly…

Decision making for self-driving cars is usually tackled by manually encoding rules from drivers' behaviors or imitating drivers' manipulation using supervised learning techniques. Both of them rely on mass driving data to cover all…

The current thesis aims to explore the reinforcement learning field and build on existing methods to produce improved ones to tackle the problem of learning in high-dimensional and complex environments. It addresses such goals by…

We address the problem of learning hierarchical deep neural network policies for reinforcement learning. In contrast to methods that explicitly restrict or cripple lower layers of a hierarchy to force them to use higher-level modulating…

Reinforcement learning (RL), known for its self-evolution capability, offers a promising approach to training high-level autonomous driving systems. However, handling constraints remains a significant challenge for existing RL algorithms,…

While deep reinforcement learning methods have shown impressive results in robot learning, their sample inefficiency makes the learning of complex, long-horizon behaviors with real robot systems infeasible. To mitigate this issue,…

Hierarchical reinforcement learning (HRL) has seen widespread interest as an approach to tractable learning of complex modular behaviors. However, existing work either assume access to expert-constructed hierarchies, or use…

We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a…

Generalizing language-conditioned multi-task imitation learning (IL) models to novel long-horizon 3D manipulation tasks is challenging. To address this, we propose DeCo (Task Decomposition and Skill Composition), a model-agnostic framework…

Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each…

Long-horizon routing tasks of deformable linear objects (DLOs), such as cables and ropes, are common in industrial assembly lines and everyday life. These tasks are particularly challenging because they require robots to manipulate DLO with…

General purpose agents will require large repertoires of skills. Empowerment -- the maximum mutual information between skills and states -- provides a pathway for learning large collections of distinct skills, but mutual information is…

Fine-tuning foundation models via reinforcement learning (RL) has proven promising for aligning to downstream objectives. In the case of diffusion models (DMs), though RL training improves alignment from early timesteps, critical issues…

We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent approaches have sought to segment trajectories into reusable skills or options, most rely on action…

Long-range navigation is commonly addressed through hierarchical pipelines in which a global planner generates a path, decomposed into waypoints, and followed sequentially by a local planner. These systems are sensitive to global path…

Reinforcement Learning (RL) based methods have been increasingly explored for robot learning. However, RL based methods often suffer from low sampling efficiency in the exploration phase, especially for long-horizon manipulation tasks, and…

Image-goal navigation steers an agent to a target location specified by an image in unseen environments. Existing methods primarily handle this task by learning an end-to-end navigation policy, which compares the similarities of target and…

Hierarchical reinforcement learning has been a compelling approach for achieving goal directed behavior over long sequences of actions. However, it has been challenging to implement in realistic or open-ended environments. A main challenge…

Hierarchical learning has been successful at learning generalizable locomotion skills on walking robots in a sample-efficient manner. However, the low-dimensional "latent" action used to communicate between two layers of the hierarchy is…

In this paper, we propose a navigation algorithm oriented to multi-agent environment. This algorithm is expressed as a hierarchical framework that contains a Hidden Markov Model (HMM) and a Deep Reinforcement Learning (DRL) structure. For…