Warning: Undefined array key "mm" in /www/wwwroot/www.ai-bt.com/si.php on line 10 Deprecated: trim(): Passing null to parameter #1 ($string) of type string is deprecated in /www/wwwroot/www.ai-bt.com/si.php on line 10 Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations.

Literature DB >> 33501023

Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations.

Abstract

Research on artificial development, reinforcement learning, and intrinsic motivations like curiosity could profit from the recently developed framework of multi-objective reinforcement learning. The combination of these ideas may lead to more realistic artificial models for life-long learning and goal directed behavior in animals and humans.

Entities: Chemical Disease Gene Species

Keywords: actor-critic design; artificial cognition; artificial curiosity; intrinsic motivation; multi-objective; reinforcement learning

Year: 2019 PMID： 33501023 PMCID： PMC7805942 DOI： 10.3389/frobt.2019.00006

Source DB: PubMed Journal: Front Robot AI ISSN： 2296-9144

19 in total

1. Artificial intelligence. Autonomous mental development by robots and animals.

Authors: J Weng; J McClelland; A Pentland; O Sporns; I Stockman; M Sur; E Thelen
Journal: Science Date: 2001-01-26 Impact factor: 47.728

2. Mastering the game of Go with deep neural networks and tree search.

Authors: David Silver; Aja Huang; Chris J Maddison; Arthur Guez; Laurent Sifre; George van den Driessche; Julian Schrittwieser; Ioannis Antonoglou; Veda Panneershelvam; Marc Lanctot; Sander Dieleman; Dominik Grewe; John Nham; Nal Kalchbrenner; Ilya Sutskever; Timothy Lillicrap; Madeleine Leach; Koray Kavukcuoglu; Thore Graepel; Demis Hassabis
Journal: Nature Date: 2016-01-28 Impact factor: 49.962

9. States versus rewards: dissociable neural prediction error signals underlying model-based and model-free reinforcement learning.

Authors: Jan Gläscher; Nathaniel Daw; Peter Dayan; John P O'Doherty
Journal: Neuron Date: 2010-05-27 Impact factor: 17.173

Review 10. Hierarchically organized behavior and its neural foundations: a reinforcement learning perspective.

Authors: Matthew M Botvinick; Yael Niv; Andew G Barto
Journal: Cognition Date: 2008-10-15

Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations.

1. Artificial intelligence. Autonomous mental development by robots and animals.

2. Mastering the game of Go with deep neural networks and tree search.

Review 3. Computational motor control in humans and robots.

4. Adaptive critic designs.

Review 5. Reinforcement learning: the good, the bad and the ugly.

Review 6. Rational and mechanistic perspectives on reinforcement learning.

Review 7. Reinforcement learning, conditioning, and the brain: Successes and challenges.

8. Learning of embodied interaction dynamics with recurrent neural networks: some exploratory experiments.

9. States versus rewards: dissociable neural prediction error signals underlying model-based and model-free reinforcement learning.

Review 10. Hierarchically organized behavior and its neural foundations: a reinforcement learning perspective.