Generative Adversarial Imitation Learning

논문 제목 : Generative Adversarial Imitation Learning(2016)

●  논문 저자 : Jonathan Ho, Stefano Ermon

●  논문 링크 : https://papers.nips.cc/paper/6391-generative-adversarial-imitation-learning.pdf

●  이전에 보면 좋은 논문 : 

○  Apprenticeship Learning via Inverse Reinforcement Learning(2004)

○  Modeling interaction via the principle of maximum causal entropy(2010) 

○  Maximum Entropy Inverse Reinforcement Learning(2008)

○  Trust region policy optimization(2015)

○  High-dimensional continuous control using generalized advantage estimation(2016)

●  함께 보면 좋은 논문 :

○  A game-theoretic approach to apprenticeship learning(2008)

○  Apprenticeship learning using linear programming(2008)

○  Nonlinear inverse reinforcement learning with gaussian processes(2011)

○  Maximum Entropy Deep Inverse Reinforcement Learning(2015)

○  Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization(2016) 

○  Model-free imitation learning with policy optimization(2016) 

○  A Connection Between GANs, Inverse Reinforcement Learning, and Energy-Based Models(2016)

---

Inverse Reinforcement Learning Travel

1. Algorithms for Inverse Reinforcement Learning(2000)
2. Apprenticeship Learning via Inverse Reinforcement Learning(2004) 
3. Maximum Margin Planning(2006)
4. Maximum Entropy Inverse Reinforcement Learning(2008)
5. Generative Adversarial Imitation Learning(2016) - Selected
6. Variational Discriminator Bottleneck(2018)

---

논문 필기 : https://www.dropbox.com/s/fdvm1yu6o1rr1ke

논문 리뷰 : https://www.dropbox.com/s/aui7notgaaeoqno/my_gail.pdf?dl=0