中文
相关论文

相关论文: Temporal Disentanglement of Representations for Im…

200 篇论文

Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper, we explore how the…

计算机视觉与模式识别 · 计算机科学 2024-10-24 Ameya Pore , Riccardo Muradore , Diego Dall'Alba

Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these misleading…

机器学习 · 计算机科学 2023-10-13 Mhairi Dunion , Trevor McInroe , Kevin Sebastian Luck , Josiah P. Hanna , Stefano V. Albrecht

The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…

机器学习 · 计算机科学 2024-02-12 Somjit Nath , Rushiv Arora , Samira Ebrahimi Kahou

The performance of image-based Reinforcement Learning (RL) agents can vary depending on the position of the camera used to capture the images. Training on multiple cameras simultaneously, including a first-person egocentric camera, can…

机器学习 · 计算机科学 2024-06-24 Mhairi Dunion , Stefano V. Albrecht

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Qi Wang , Zhipeng Zhang , Baao Xie , Xin Jin , Yunbo Wang , Shiyu Wang , Liaomo Zheng , Xiaokang Yang , Wenjun Zeng

In an effort to overcome limitations of reward-driven feature learning in deep reinforcement learning (RL) from images, we propose decoupling representation learning from policy learning. To this end, we introduce a new unsupervised…

机器学习 · 计算机科学 2021-05-18 Adam Stooke , Kimin Lee , Pieter Abbeel , Michael Laskin

Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To…

机器学习 · 计算机科学 2024-02-19 Moritz Lange , Noah Krystiniak , Raphael C. Engelhardt , Wolfgang Konen , Laurenz Wiskott

Intelligent perception and interaction with the world hinges on internal representations that capture its underlying structure (''disentangled'' or ''abstract'' representations). Disentangled representations serve as world models, isolating…

机器学习 · 计算机科学 2025-03-04 Pantelis Vafidis , Aman Bhargava , Antonio Rangel

Agents that are aware of the separation between themselves and their environments can leverage this understanding to form effective representations of visual input. We propose an approach for learning such structured representations for RL…

机器学习 · 计算机科学 2023-09-06 Kevin Gmelin , Shikhar Bahl , Russell Mendonca , Deepak Pathak

Reinforcement learning (RL) algorithms can find an optimal policy for a single agent to accomplish a particular task. However, many real-world problems require multiple agents to collaborate in order to achieve a common goal. For example, a…

机器学习 · 计算机科学 2025-10-20 Jan Corazza , Hadi Partovi Aria , Hyohun Kim , Daniel Neider , Zhe Xu

Intelligent agents should be able to learn useful representations by observing changes in their environment. We model such observations as pairs of non-i.i.d. images sharing at least one of the underlying factors of variation. First, we…

Goal-Conditioned Reinforcement Learning (GCRL) can enable agents to spontaneously set diverse goals to learn a set of skills. Despite the excellent works proposed in various fields, reaching distant goals in temporally extended tasks…

机器人学 · 计算机科学 2023-07-21 Zhifeng Qian , Mingyu You , Hongjun Zhou , Xuanhui Xu , Bin He

Reinforcement Learning (RL) enables an intelligent agent to optimise its performance in a task by continuously taking action from an observed state and receiving a feedback from the environment in form of rewards. RL typically uses tables…

人工智能 · 计算机科学 2025-01-28 Alberto Castagna

Solving a reinforcement learning (RL) problem poses two competing challenges: fitting a potentially discontinuous value function, and generalizing well to new observations. In this paper, we analyze the learning dynamics of temporal…

机器学习 · 计算机科学 2022-06-07 Clare Lyle , Mark Rowland , Will Dabney , Marta Kwiatkowska , Yarin Gal

Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…

机器学习 · 计算机科学 2025-05-16 Jonathan Clifford Balloch

Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using…

计算机视觉与模式识别 · 计算机科学 2022-08-01 Xiao Liu , Pedro Sanchez , Spyridon Thermos , Alison Q. O'Neil , Sotirios A. Tsaftaris

We propose a novel framework for multi-task reinforcement learning (MTRL). Using a variational inference formulation, we learn policies that generalize across both changing dynamics and goals. The resulting policies are parametrized by…

机器学习 · 计算机科学 2019-06-24 Janith C. Petangoda , Sergio Pascual-Diaz , Vincent Adam , Peter Vrancx , Jordi Grau-Moya

Text-based reinforcement learning involves an agent interacting with a fictional environment using observed text and admissible actions in natural language to complete a task. Previous works have shown that agents can succeed in text-based…

计算与语言 · 计算机科学 2024-04-17 Mauricio Gruppi , Soham Dan , Keerthiram Murugesan , Subhajit Chaudhury

Deep reinforcement learning (RL) agents that exist in high-dimensional state spaces, such as those composed of images, have interconnected learning burdens. Agents must learn an action-selection policy that completes their given task, which…

机器学习 · 计算机科学 2021-10-12 Trevor McInroe , Lukas Schäfer , Stefano V. Albrecht

Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. It is known that variations in input domains (e.g., different panorama colors due to seasonal changes) or task…

机器学习 · 计算机科学 2025-02-19 Antonio Pio Ricciardi , Valentino Maiorca , Luca Moschella , Riccardo Marin , Emanuele Rodolà
‹ 上一页 1 2 3 10 下一页 ›