反向学习

除了直接学习 Reward，还可以从示例中学习奖励函数。这就是反向强化学习。

课程材料

• 滑铁卢 CS885 RL PPT
• Berkeley CS285 Lec 20: Inverse Reinforcement Learning, slides, Youtube Video

• Berkeley Deep RL Bootcamp 2017, Lecture 10b Inverse RL – Chelsea Finn (video

  slides)

论文

滑铁卢 Inverse RL

• Ziebart, B. D., Bagnell, J. A., & Dey, A. K. (2010). Modeling interaction via the principle of maximum causal entropy. In ICML.
• Finn, C., Levine, S., & Abbeel, P. (2016). Guided cost learning: Deep inverse optimal control via policy optimization. In ICML (pp. 49-58).

课本材料

N/A

练习

N/A