Apprenticeship Learning - Inverse Reinforcement Learning (IRL)

From
Revision as of 07:27, 4 August 2018 by BPeat (talk | contribs)
Jump to: navigation, search

YouTube 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.