Difference between revisions of "Apprenticeship Learning - Inverse Reinforcement Learning (IRL)"
| Line 2: | Line 2: | ||
* [[Reinforcement Learning]] | * [[Reinforcement Learning]] | ||
| + | * [[Generative Adversarial Network (GAN)]] | ||
* [http://arxiv.org/pdf/1806.06877.pdf A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress | Saurabh Arora, Prashant Doshi] 18 Jun 2018 | * [http://arxiv.org/pdf/1806.06877.pdf A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress | Saurabh Arora, Prashant Doshi] 18 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 | * [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/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. | ||
| + | |||
| + | |||
| + | <youtube>0q30_gDlrwk</youtube> | ||
<youtube>h7uGyBcIeII</youtube> | <youtube>h7uGyBcIeII</youtube> | ||
<youtube>d9DlQSJQAoI</youtube> | <youtube>d9DlQSJQAoI</youtube> | ||
<youtube>JbNeLiNnvII</youtube> | <youtube>JbNeLiNnvII</youtube> | ||
<youtube>f9UpSJdWwkQ</youtube> | <youtube>f9UpSJdWwkQ</youtube> | ||
| − | + | <youtube>giH0wWOXX_E</youtube> | |
| − | <youtube> | + | <youtube>xNvNeg7JGSM</youtube> |
| − | <youtube> | + | <youtube>fu7uBNWTzU8</youtube> |
Revision as of 07:27, 4 August 2018
- Reinforcement Learning
- Generative Adversarial Network (GAN)
- 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/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.
