English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Talk

The Consilience of Neural and Artificial Reinforcement Learning

MPS-Authors
There are no MPG-Authors available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Dayan, P. (2017). The Consilience of Neural and Artificial Reinforcement Learning. Talk presented at Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17). San Francisco, CA, USA. 2017-02-04 - 2017-02-09.


Cite as: http://hdl.handle.net/21.11116/0000-0003-E821-2
Abstract
Animals that fail to predict or control events associated with rewards and punishments are not long for this world. Reinforcement learning thus offers a body of theory that organizes and motivates a huge wealth of work in psychology and neuroscience. Equally, these latter disciplines provide inspiration for new methods, ideas and problems in the wider field of reinforcement learning. I will discuss this consilience, illustrating the fecundity of the approaches and some of the challenges and opportunities ahead.