Inverse Reinforcement Learning 总结

目录​​​​​​​

文献

Imitation Learning

IRL

Maximum Entropy Inverse Reinforcement Learning

Generative Adversarial Imitation Learning (GAIL)

---

文献

逆向强化学习（Inverse Reinforcement Learning）简介 - 知乎

Deep RL Bootcamp Lecture 10B Inverse Reinforcement Learning

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

Generative Adversarial Imitation Learning

Learning human behaviors from motion capture by adversarial imitation

A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models

强化学习进阶 第十讲 逆向强化学习（第三节 基于最大熵的方法） - 知乎

Ziebart, B., Maas, A., Bagnell, A., and Dey, A. (2008). Maximum Entropy Inverse Reinforcement Learning. In Proceedings of The Twenty-third AAAI Conference on Artificial Intelligence (AAAI'08), pages 1433-1438.

Boularias, A., Kober, J., and Peters, J. Relative entropy inverse reinforcement learning. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2011.

https://www.zhihu.com/question/276857379/answer/391042285

https://www.zhihu.com/question/276857379/answer/390369897

https://www.zhihu.com/question/276857379/answer/399538013

传统算法有feature matching IRL，参考Abbeel & Ng:Apprenticeship learning via inverse reinforcement learning

当代算法有MaxEnt IRL algorithm。参考MaxEnt IRL with hand-designed features for learning to navigate in urban environments based on taxi cab GPS data.

Watch This: Scalable Cost-Function Learning for Path Planning in Urban Environments