- 15.1. Supervised Imitation Learning
- 15.2. DAgger
- 15.2. Understanding DAgger
- 15.3. Algorithm - DAgger
- 15.3. Deep Q learning from Demonstrations
- 15.3.1. Phases of DQfD
- 15.3.2. Loss Function of DQfD
- 15.3.3. Algorithm - DQfD
- 15.4. Inverse Reinforcement Learning
- 15.5. Maximum Entropy IRL
- 15.5.1. Key Terms
- 15.5.2. Back to Max entropy IRL
- 15.5.3. Computing the Gradient
- 15.5.4. Algorithm - Maximum Entropy IRL
- 15.6. Generative Adversarial Imitation Learning
- 15.6.1. Formulation of GAIL