相关论文: MoVie: Visual Model-Based Policy Adaptation for Vi…

A general-purpose robot should be able to master a wide range of tasks and quickly learn a novel one by leveraging past experiences. One-shot imitation learning (OSIL) approaches this goal by training an agent with (pairs of) expert…

Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For instance, when a textual description of a scene is given,…

Virtual character animation control is a problem for which Reinforcement Learning (RL) is a viable approach. While current work have applied RL effectively to portray physics-based skills, social behaviours are challenging to design reward…

A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. Existing robust methods try to obtain a fixed policy for all envisioned dynamic…

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…

A primary challenge for visual-based Reinforcement Learning (RL) is to generalize effectively across unseen environments. Although previous studies have explored different auxiliary tasks to enhance generalization, few adopt image…

In this work, we investigate Active Vision Reinforcement Learning (ActiveVision-RL), where an embodied agent simultaneously learns action policy for the task while also controlling its visual observations in partially observable…

Reward function specification, which requires considerable human effort and iteration, remains a major impediment for learning behaviors through deep reinforcement learning. In contrast, providing visual demonstrations of desired behaviors…

We study how to generalize the visuomotor policy of a mobile manipulator from the perspective of visual observations. The mobile manipulator is prone to occlusion owing to its own body when only a single viewpoint is employed and a…

Vision-Language-Action (VLA) models empower robots to understand and execute tasks described by natural language instructions. However, a key challenge lies in their ability to generalize beyond the specific environments and conditions they…

A commercial robot, trained by its manufacturer to recognize a predefined number and type of objects, might be used in many settings, that will in general differ in their illumination conditions, background, type and degree of clutter, and…

Vision-based reinforcement learning (RL) is a promising approach 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 physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requires the agent to consistently adapt to novel tasks without…

Unlike quasi-static robotic manipulation tasks like pick-and-place, dynamic tasks such as non-prehensile manipulation pose greater challenges, especially for vision-based control. Successful control requires the extraction of features…

In everyday life collaboration tasks between human operators and robots, the former necessitate simple ways for programming new skills, the latter have to show adaptive capabilities to cope with environmental changes. The joint use of…

Learned language-conditioned robot policies often struggle to effectively adapt to new real-world tasks even when pre-trained across a diverse set of instructions. We propose a novel approach for few-shot adaptation to unseen tasks that…

A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotics, obtaining such rewards typically requires either labor-intensive human labeling or brittle, handcrafted objectives.…

General-purpose robotic manipulation, including reach and grasp, is essential for deployment into households and workspaces involving diverse and evolving tasks. Recent advances propose using large pre-trained models, such as Large Language…

We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language…

Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for learning policies is the same as the environment for…