Week 12: April 7-April 14

Interactive session, Wednesday April 7

• Zoom link (needs UiO login)
• Anonymous feedback and suggestions
• No Recording

Weekly lecture:

Slides:

Reinforcement learning

Videos:

1. The reinforcement learning problem
2. Reward and action selection
3. Policy and value
4. The q-learning algorithm
5. Q-learning example
6. On-policy and off-policy learning

Readings:

Marsland Chapter 11

Optional Reading

The readings below go beyond the syllabus for this class, so do not worry if you don't understand everything. But, it can provide some interesting perspectives if you want to dig deeper into RL.

From Q-Learning to Deep Q-Learning: https://towardsdatascience.com/reinforcement-learning-tutorial-part-3-basic-deep-q-learning-186164c3bf4

The Paths Perspective on Value Learning: https://distill.pub/2019/paths-perspective-on-value-learning/

(Advanced) Article showing important limitations of state-of-the-art Reinforcement Learning: https://thegradient.pub/why-rl-is-flawed/

Weekly exercises

• Exercises
• Solution
• All group sessions will be digital this week.