<--- Back to Details
First PageDocument Content
Algorithm / Machine learning / Marcus Hutter / Reinforcement learning
Date: 2011-01-24 13:03:15
Algorithm
Machine learning
Marcus Hutter
Reinforcement learning

Journal of Artificial Intelligence Research Submitted 07/10; publishedA Monte-Carlo AIXI Approximation Joel Veness

Add to Reading List

Source URL: jair.org

Download Document from Source Website

File Size: 668,25 KB

Share Document on Facebook

Similar Documents

Can Intelligence Explode? Marcus Hutter Research School of Computer Science Australian National University  Department of Computer Science

Can Intelligence Explode? Marcus Hutter Research School of Computer Science Australian National University Department of Computer Science

DocID: 1u1XH - View Document

Discriminative Hierarchical Rank Pooling for Activity Recognition Basura Fernando, Peter Anderson, Marcus Hutter, Stephen Gould The Australian National University Canberra, Australia

Discriminative Hierarchical Rank Pooling for Activity Recognition Basura Fernando, Peter Anderson, Marcus Hutter, Stephen Gould The Australian National University Canberra, Australia

DocID: 1tFw6 - View Document

A Formal Definition of Intelligence for Artificial Systems Shane Legg and Marcus Hutter IDSIA, Galleria 2, Manno-Lugano 6928, Switzerland {shane,marcus}@idsia.ch  A fundamental difficulty in artificial intelligence is th

A Formal Definition of Intelligence for Artificial Systems Shane Legg and Marcus Hutter IDSIA, Galleria 2, Manno-Lugano 6928, Switzerland {shane,marcus}@idsia.ch A fundamental difficulty in artificial intelligence is th

DocID: 1tpOU - View Document

A Universal Measure of Intelligence for Artificial Agents∗ Shane Legg and Marcus Hutter IDSIA, Galleria 2, Manno-Lugano 6928, Switzerland {shane,marcus}@idsia.ch

A Universal Measure of Intelligence for Artificial Agents∗ Shane Legg and Marcus Hutter IDSIA, Galleria 2, Manno-Lugano 6928, Switzerland {shane,marcus}@idsia.ch

DocID: 1sPJP - View Document

Avoiding Wireheading with Value Reinforcement Learning1 Tom Everitt tomeveritt.se Australian National University

Avoiding Wireheading with Value Reinforcement Learning1 Tom Everitt tomeveritt.se Australian National University

DocID: 1ragO - View Document