相关论文: SegDAC: Visual Generalization in Reinforcement Lea…

We propose a fully distributed actor-critic algorithm approximated by deep neural networks, named \textit{Diff-DAC}, with application to single-task and to average multitask reinforcement learning (MRL). Each agent has access to data from…

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe…

Future advancements in robot autonomy and sophistication of robotics tasks rest on robust, efficient, and task-dependent semantic understanding of the environment. Semantic segmentation is the problem of simultaneous segmentation and…

Producing agents that can generalize to a wide range of visually different environments is a significant challenge in reinforcement learning. One method for overcoming this issue is visual domain randomization, whereby at the start of each…

Learning a shared policy that guides the locomotion of different agents is of core interest in Reinforcement Learning (RL), which leads to the study of morphology-agnostic RL. However, existing benchmarks are highly restrictive in the…

Existing reinforcement learning (RL) methods struggle with long-horizon robotic manipulation tasks, particularly those involving sparse rewards. While action chunking is a promising paradigm for robotic manipulation, using RL to directly…

Visuomotor policies learned from demonstrations often overfit to nuisance visual factors in raw RGB observations, resulting in brittle behavior under appearance shifts such as background changes and object recoloring. We propose a…

A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or…

We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some…

Text-based games (TBGs) have become a popular proving ground for the demonstration of learning-based agents that make decisions in quasi real-world settings. The crux of the problem for a reinforcement learning agent in such TBGs is…

This paper presents GenDoc, a general sequence-to-sequence document understanding model pre-trained with unified masking across three modalities: text, image, and layout. The proposed model utilizes an encoder-decoder architecture, which…

Learning task-oriented dialog policies via reinforcement learning typically requires large amounts of interaction with users, which in practice renders such methods unusable for real-world applications. In order to reduce the data…

Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for expensive online learning. Despite strong generalization in…

Deep reinforcement learning (RL) has proven a powerful technique in many sequential decision making domains. However, Robotics poses many challenges for RL, most notably training on a physical system can be expensive and dangerous, which…

The rapid increase in the amount of published visual data and the limited time of users bring the demand for processing untrimmed videos to produce shorter versions that convey the same information. Despite the remarkable progress that has…

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a…

Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose \textbf{VideoSeg-R1}, the first…

Training a model-free deep reinforcement learning model to solve image-to-image translation is difficult since it involves high-dimensional continuous state and action spaces. In this paper, we draw inspiration from the recent success of…

Vision-based robotics often separates the control loop into one module for perception and a separate module for control. It is possible to train the whole system end-to-end (e.g. with deep RL), but doing it "from scratch" comes with a high…

Episodic training, where an agent's environment is reset after every success or failure, is the de facto standard when training embodied reinforcement learning (RL) agents. The underlying assumption that the environment can be easily reset…