Difference between revisions of "Reinforcement learning"

From Lesswrongwiki
Jump to: navigation, search
(Created page with "{{wikilink}} '''Reinforcement Learning''' == Further Reading & References== ==See Also== *Machine learning *Friendly AI *Game theory *Prediction")
 
Line 1: Line 1:
 
{{wikilink}}
 
{{wikilink}}
'''Reinforcement Learning'''  
+
Within the field of Machine learning, '''reinforcement learning''' refers to the study of methods of magnifying the reward given by interactions with the environment with no a priori knowledge of its properties. Strongly inspired by the work developed in behavioral psychology it is essentially a trial and error approach to find the best strategy.
 
 
== Further Reading & References==
 
  
 +
Consider an agent that receives an input vector – ''I'' – from a complex environment of which it knows nothing of – ''S'' – informing it of its state. Based only on that information, the agent has to make a decision regarding and action which will influence the state of the environment – ''A''. This action will in itself change the state of the environment, which will result in a new input vector, and so on, each time also presenting the agent with the reward relative to its actions in the environment – ''r''. The agent goal is then to find the ideal strategy which will give the highest reward expectations over time, based on previous experience.
  
 
==See Also==
 
==See Also==
 
 
*[[Machine learning]]
 
*[[Machine learning]]
 
*[[Friendly AI]]
 
*[[Friendly AI]]
 
*[[Game theory]]
 
*[[Game theory]]
 
*[[Prediction]]
 
*[[Prediction]]

Revision as of 00:02, 14 September 2012

Smallwikipedialogo.png
Wikipedia has an article about

Within the field of Machine learning, reinforcement learning refers to the study of methods of magnifying the reward given by interactions with the environment with no a priori knowledge of its properties. Strongly inspired by the work developed in behavioral psychology it is essentially a trial and error approach to find the best strategy.

Consider an agent that receives an input vector – I – from a complex environment of which it knows nothing of – S – informing it of its state. Based only on that information, the agent has to make a decision regarding and action which will influence the state of the environment – A. This action will in itself change the state of the environment, which will result in a new input vector, and so on, each time also presenting the agent with the reward relative to its actions in the environment – r. The agent goal is then to find the ideal strategy which will give the highest reward expectations over time, based on previous experience.

See Also