Difference between revisions of "Apprenticeship Learning - Inverse Reinforcement Learning (IRL)"

From
Jump to: navigation, search
m
m
Line 25: Line 25:
 
<youtube>JbNeLiNnvII</youtube>
 
<youtube>JbNeLiNnvII</youtube>
 
<youtube>f9UpSJdWwkQ</youtube>
 
<youtube>f9UpSJdWwkQ</youtube>
<youtube>giH0wWOXX_E</youtube>
 
 
<youtube>xNvNeg7JGSM</youtube>
 
<youtube>xNvNeg7JGSM</youtube>
 
<youtube>fu7uBNWTzU8</youtube>
 
<youtube>fu7uBNWTzU8</youtube>

Revision as of 08:44, 8 February 2022

YouTube search... ...Google search


Inverse reinforcement learning (IRL) infers/derives a reward function from observed behavior/demonstrations, allowing for policy improvement and generalization. While ordinary "reinforcement learning" involves using rewards and punishments to learn behavior, in IRL the direction is reversed, and a robot observes a person's behavior to figure out what goal that behavior seems to be trying to achieve.