5. Reinforcement learning

3 dezembro 2019, 09:00 • Francisco Melo

Tabular solution methods:

7. n-step bootstrapping (Chap. 7)

8. Eligibility traces (Chap. 12)

9. Planning and learning with tabular methods (Chap. 8)

4. Reinforcement learning

26 novembro 2019, 09:00 • Francisco Melo

Tabular solution methods (cont.):

5. Monte-Carlo methods (Chap. 5)

6. Temporal-difference learning (Chap. 6)

3. Markov decision processes (cont.)

19 novembro 2019, 09:00 • Francisco Melo

Tabular solution methods (cont.):

4. Dynamic programming (Chap. 4)

2. Markov decision processes

12 novembro 2019, 09:00 • Francisco Melo

Tabular solution methods (cont.):

3. Finite Markov decision processes (Chap. 3)

1. Introduction to reinforcement learning

5 novembro 2019, 09:00 • Francisco Melo

Course overview. Tabular solution methods:

1. What is reinforcement learning? (Chap. 1)

2. Multi-armed bandits (Chap. 2)