Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Houthooft, Rein"'
Autor:
Stadie, Bradly C., Yang, Ge, Houthooft, Rein, Chen, Xi, Duan, Yan, Wu, Yuhuai, Abbeel, Pieter, Sutskever, Ilya
We consider the problem of exploration in meta reinforcement learning. Two new meta reinforcement learning algorithms are suggested: E-MAML and E-$\text{RL}^2$. Results are presented on a novel environment we call `Krazy World' and a set of maze envi
Externí odkaz:
http://arxiv.org/abs/1803.01118
Autor:
Houthooft, Rein, Chen, Richard Y., Isola, Phillip, Stadie, Bradly C., Wolski, Filip, Ho, Jonathan, Abbeel, Pieter
We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, which optimizes its policy to minimize this loss, will achieve high rewar
Externí odkaz:
http://arxiv.org/abs/1802.04821
Autor:
Plappert, Matthias, Houthooft, Rein, Dhariwal, Prafulla, Sidor, Szymon, Chen, Richard Y., Chen, Xi, Asfour, Tamim, Abbeel, Pieter, Andrychowicz, Marcin
Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a rich
Externí odkaz:
http://arxiv.org/abs/1706.01905
Autor:
Tang, Haoran, Houthooft, Rein, Foote, Davis, Stooke, Adam, Chen, Xi, Duan, Yan, Schulman, John, De Turck, Filip, Abbeel, Pieter
Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based met
Externí odkaz:
http://arxiv.org/abs/1611.04717
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that also maxim
Externí odkaz:
http://arxiv.org/abs/1606.03657
Scalable and effective exploration remains a key challenge in reinforcement learning (RL). While there are methods with optimality guarantees in the setting of discrete state and action spaces, these methods cannot be applied in high-dimensional deep
Externí odkaz:
http://arxiv.org/abs/1605.09674
Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari games based on raw pixel data a
Externí odkaz:
http://arxiv.org/abs/1604.06778
Autor:
Houthooft, Rein, De Turck, Filip
Tackling pattern recognition problems in areas such as computer vision, bioinformatics, speech or text recognition is often done best by taking into account task-specific statistical relations between output variables. In structured prediction, this
Externí odkaz:
http://arxiv.org/abs/1508.00451
Autor:
Houthooft, Rein, De Turck, Filip
Publikováno v:
In Pattern Recognition November 2016 59:292-301
Autor:
Houthooft, Rein, Ruyssinck, Joeri, van der Herten, Joachim, Stijven, Sean, Couckuyt, Ivo, Gadeyne, Bram, Ongenae, Femke, Colpaert, Kirsten, Decruyenaere, Johan, Dhaene, Tom, De Turck, Filip
Publikováno v:
In Artificial Intelligence In Medicine March 2015 63(3):191-207