Difference between revisions of "Apprenticeship Learning - Inverse Reinforcement Learning (IRL)"
m |
m |
||
| Line 14: | Line 14: | ||
* [[Generative Adversarial Network (GAN)]] | * [[Generative Adversarial Network (GAN)]] | ||
* [[Connecting Brains]] | * [[Connecting Brains]] | ||
| − | * [[Policy]] | + | * [[Policy]] ... [[Policy vs Plan]] ... [[Constitutional AI]] ... [[Trust Region Policy Optimization (TRPO)]] ... [[Policy Gradient (PG)]] ... [[Proximal Policy Optimization (PPO)]] |
* [[Generative AI]] ... [[Conversational AI]] ... [[OpenAI]]'s [[ChatGPT]] ... [[Perplexity]] ... [[Microsoft]]'s [[Bing]] ... [[You]] ...[[Google]]'s [[Bard]] ... [[Baidu]]'s [[Ernie]] | * [[Generative AI]] ... [[Conversational AI]] ... [[OpenAI]]'s [[ChatGPT]] ... [[Perplexity]] ... [[Microsoft]]'s [[Bing]] ... [[You]] ...[[Google]]'s [[Bard]] ... [[Baidu]]'s [[Ernie]] | ||
* [https://arxiv.org/pdf/1806.06877.pdf A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress | Saurabh Arora, Prashant Doshi] 18 Jun 2018 | * [https://arxiv.org/pdf/1806.06877.pdf A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress | Saurabh Arora, Prashant Doshi] 18 Jun 2018 | ||
Revision as of 16:34, 16 April 2023
YouTube search... ...Google search
- Learning Techniques
- Inside Out - Curious Optimistic Reasoning
- Generative Adversarial Network (GAN)
- Connecting Brains
- Policy ... Policy vs Plan ... Constitutional AI ... Trust Region Policy Optimization (TRPO) ... Policy Gradient (PG) ... Proximal Policy Optimization (PPO)
- Generative AI ... Conversational AI ... OpenAI's ChatGPT ... Perplexity ... Microsoft's Bing ... You ...Google's Bard ... Baidu's Ernie
- 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
- Guide to MBIRL – Model Based Inverse Reinforcement Learning | Aishwarya Verma
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.
