Difference between revisions of "Apprenticeship Learning - Inverse Reinforcement Learning (IRL)"
| Line 5: | Line 5: | ||
* [http://arxiv.org/pdf/1805.07687.pdf Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications | Daniel S. Brown, Scott Niekum] 23 Jun 2018 | * [http://arxiv.org/pdf/1805.07687.pdf Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications | Daniel S. Brown, Scott Niekum] 23 Jun 2018 | ||
| − | Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. | + | Inverse reinforcement learning (IRL) infers/deriving 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. |
<youtube>h7uGyBcIeII</youtube> | <youtube>h7uGyBcIeII</youtube> | ||
Revision as of 07:17, 4 August 2018
- Reinforcement Learning
- A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress | Saurabh Arora, Prashant Doshi 18 Jun 2018
- Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications | Daniel S. Brown, Scott Niekum 23 Jun 2018
Inverse reinforcement learning (IRL) infers/deriving 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.
