Columbia 2015: Learning to Control

  1. Lecture: Introduction [slides]
  2. Lecture: Robotics in a nutshell [slides]
  3. Lecture: Machine learning in a few minutes [slides1], [slides2]
  4. Lecture: Model Learning [slides]
  5. Lecture: Imitation Learning by Behavioral Cloning [slides]
  6. Lecture: Optimal Control of Discrete Systems [slides]
  7. Lecture: Optimal Control of Continuous Systems [slides]
  8. Lecture: Value Function Methods [slides]
  9. Lecture: Policy Search with Policy Gradients [slides]
  10. Lecture: Probabilistic Policy Search [slides]
  11. Lecture: Imitation Learning by Inverse Reinforcement Learning [slides]


zum Seitenanfang