Algorithms for Policy Learning

---

Topics and Objectives (Apr 15 – Apr 19)

• Policy evaluation vs. policy Learning
• Policy Iteration
• Temporal Difference Learning
• SARSA and Q-Learning
• On-line vs. Off-line
• On-Policy vs. Off-Policy
• Exploration vs. Exploitation

---

Lecture Notes

• Policy Iteration
• Frozen Lake Example in Python [Source File]
• Temporal Difference Learning

---

Homework

• See Homework 5 for details
• This is our last set of homework.

---