相关论文: Leveraging Locality to Boost Sample Efficiency in …

Reinforcement learning has been demonstrated as a flexible and effective approach for learning a range of continuous control tasks, such as those used by robots to manipulate objects in their environment. But in robotics particularly,…

Reinforcement learning (RL) suffers from low sample efficiency, particularly in high-dimensional continuous state-action spaces of complex robotic manipulation tasks. RL performance can improve by leveraging prior knowledge, even when…

Imitation learning is a popular paradigm to teach robots new tasks, but collecting robot demonstrations through teleoperation or kinesthetic teaching is tedious and time-consuming. In contrast, directly demonstrating a task using our human…

Reinforcement learning (RL) agents can learn to solve complex tasks from visual inputs, but generalizing these learned skills to new environments remains a major challenge in RL application, especially robotics. While data augmentation can…

Vision-based reinforcement learning (RL) is a promising technique to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Learning robust and generalizable manipulation skills from demonstrations remains a key challenge in robotics, with broad applications in industrial automation and service robotics. While recent imitation learning methods have achieved…

Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications, and in particular for visuo-motor control. Model-based RL has the potential to be highly…

Learning-based robotic systems demand rigorous validation to assure reliable performance, but extensive real-world testing is often prohibitively expensive, and if conducted may still yield insufficient data for high-confidence guarantees.…

For reinforcement learning in data-scarce domains like real-world robotics, intensive data reuse enhances efficiency but induces overfitting. While prior works focus on critic bias, representation-level instability in Self-Predictive…

In this work, we study how to build a robotic system that can solve multiple 3D manipulation tasks given language instructions. To be useful in industrial and household domains, such a system should be capable of learning new tasks with few…

Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency, particularly in real-world scenarios with costly physical interactions. This paper introduces a novel human-inspired framework to…

Sample efficiency remains a crucial challenge in applying Reinforcement Learning (RL) to real-world tasks. While recent algorithms have made significant strides in improving sample efficiency, none have achieved consistently superior…

The performance of robotic imitation learning is fundamentally limited by data quality and training strategies. Prevalent sampling strategies on RLBench suffer from severe keyframe redundancy and imbalanced temporal distribution, leading to…

An excellent representation is crucial for reinforcement learning (RL) performance, especially in vision-based reinforcement learning tasks. The quality of the environment representation directly influences the achievement of the learning…

Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching or teleoperation prohibitively restrict…

Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this…

Vision-Language-Action (VLA) models show promise for robotic control, yet performance in complex household environments remains sub-optimal. Mobile manipulation requires reasoning about global scene layout, fine-grained geometry, and…

Given the task of learning robotic grasping solely based on a depth camera input and gripper force feedback, we derive a learning algorithm from an applied point of view to significantly reduce the amount of required training data. Major…

The ability of neural networks to perform robotic perception and control tasks such as depth and optical flow estimation, simultaneous localization and mapping (SLAM), and automatic control has led to their widespread adoption in recent…

This paper introduces an open-source, decentralized framework named SigmaRL, designed to enhance both sample efficiency and generalization of multi-agent Reinforcement Learning (RL) for motion planning of connected and automated vehicles.…