Buscar recursos académicos

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad...

An account of key ideas and algorithms in reinforcement learning. The discussion ranges from the history of the field's intellectual foundations to recent developments and applications. Areas studied include reinforcemen...

Materias / palabras clave: Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Machine learning; Psychology; Social psychology

Materias / palabras clave: Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Engineering; Structural engineering

Materias / palabras clave: Reinforcement learning; Computer science; Artificial intelligence; Variety (cybernetics); Deep learning; Control (management); Perception; Human–computer interaction; Machine learning; Neuroscience; Biology

Software agents are programs that can observe their environment and act in an attempt to reach their design goals. In most cases the selection of particular agent architecture determines the behaviour in response to the ...

Due to the safety risks and training sample inefficiency, it is often preferred to develop controllers in simulation. However, minor differences between the simulation and the real world can cause a significant sim-to-re...

"Very few learning systems applied to problem solving have focused on learning operator definitions from the interaction with a completely unknown environment. In order to achieve better learning convergence, several age...

"What should be the sensing capabilities of agents in a Multi-Agent System be to solve a problem efficiently, quickly and economicly? This question often appears when trying to solve a problem using Multi-Agent Systems. ...

Q-Learning is a Reinforcement Learning method for solving sequential decision problems, where the utility of actions depends on a sequence of decisions and there exists uncertainty about the dynamics of the environment t...

Materias / palabras clave: Artificial intelligence; Deep learning; Computer science; Artificial neural network; Backpropagation; Reinforcement learning; Machine learning; Deep neural networks; Unsupervised learning; Recurrent neural network; Encod...

The proceedings of the 2001 Neural Information Processing Systems (NIPS) Conference. The annual conference on Neural Information Processing Systems (NIPS) is the flagship conference on neural computation. The conference ...

The long-anticipated revision of this #1 selling book offers the most comprehensive, state of the art introduction to the theory and practice of artificial intelligence for modern applications. Intelligent Agents. Solvin...

Cache-coherent, nonumiform memory acces or cc-NUMA is an attractive architecture for building a spectrum of shared memory multiprocessors (whic are socing widespread use in commercial, technical and scientific applicatio...

Materias / palabras clave: Monte Carlo tree search; Computer science; Champion; Artificial neural network; Reinforcement learning; Artificial intelligence; Game tree; Value (mathematics); Search algorithm; Tree (set theory); Deep neural networks; ...

Materias / palabras clave: Champion; Artificial intelligence; Artificial neural network; Reinforcement learning; Computer science; Selection (genetic algorithm); Tree (set theory); Machine learning; Domain (mathematical analysis); Mathematics; Pol...

Options have been shown to be a key step in extending reinforcement learning beyond low-level reactionary systems to higher-level, planning systems. Most of the options research involves hand-crafted options; there has b...

"Error-related potential (ErrP) are a particular type of Event-Related Potential (ERP) elicited by a person attending a recognizable error. These Electroencephalographic (EEG) signals can be used to train a gaming agent ...

Papers from the 2006 flagship meeting on neural computation, with contributions from physicists, neuroscientists, mathematicians, statisticians, and computer scientists. The annual Neural Information Processing Systems (...

We propose a technique for producing `visual explanations' for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent. Our approach - Gradient-weighted Class Activat...