paper-with-me

Papers

COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration

2019-05-22 · Nicholas Watters, Loic Matthey, Matko Bosnjak, Christopher P. Burgess, Alexander Lerchner

Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms. Here we introduce a modular approach to addressing these challenges in a continuous control environment, without using hand-crafted or supervised information. Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured hold-out tests of policy robustness.

📄 PDF Abstract BibTeX arXiv:1905.09275

Code (2)

deepmind/spriteworld 공식 구현
google-deepmind/spriteworld

Tasks

continuous-controlContinuous ControlDeep Reinforcement LearningObjectObject Discoveryreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Crater Observing Bio-inspired Rolling Articulator (COBRA)

2025-09-23 · Adarsh Salagame, Henry Noyes, Alireza Ramezani, Eric Sihite 외 arxiv

NASA aims to establish a sustainable human basecamp on the Moon as a stepping stone for future missions to Mars and beyond. The discovery of water ice on the Moon's craters located in permanently shadowed regions, which …

Solving the G-problems in less than 500 iterations: Improved efficient constrained optimization by surrogate modeling and adaptive parameter control

2015-12-31 · Samineh Bagheri, Wolfgang Konen, Michael Emmerich, Thomas Bäck

Constrained optimization of high-dimensional numerical problems plays an important role in many scientific and industrial applications. Function evaluations in many industrial applications are severely limited and no ana…

Cobra: Efficient Line Art COlorization with BRoAder References

2025-04-16 · Junhao Zhuang, Lingen Li, Xuan Ju, Zhaoyang Zhang 외

The comic production industry requires reference-based line art colorization with high accuracy, efficiency, contextual consistency, and flexible control. A comic page often involves diverse characters, objects, and back…

ColorizationImage GenerationLine Art Colorization

COBRA: Context-aware Bernoulli Neural Networks for Reputation Assessment

2019-12-18 · Leonit Zeynalvand, Tie Luo, Jie Zhang

Trust and reputation management (TRM) plays an increasingly important role in large-scale online environments such as multi-agent systems (MAS) and the Internet of Things (IoT). One main objective of TRM is to achieve ac…

BIG-bench Machine LearningManagement

Controlling Travel Path of Original Cobra

2022-10-15 · Mriganka Basu RoyChowdhury, Arabin K Dey

In this paper we propose a kernel based COBRA which is a direct approximation of the original COBRA. We propose a novel tuning procedure for original COBRA parameters based on this kernel approximation. We show that our …