A list of exercises for the Robot Learning course.
Links:
Contents:
- Tic-tac-toe
Links:
Contents:
- Seven-armed bandit
Links:
Contents:
- Policy Iteration algorithm
- Value Iteration algorithm
Links:
Contents:
- Monte Carlo Policy Evaluation
- Monte Carlo Policy Control
Links:
Contents:
- ε-greedy action selection
- Q-learning
Links:
Contents:
- Sarsa
- BeCareful game
Links:
Contents:
- Policy gradient method
Links:
Contents:
- Linear Quadratic Regulation (LQR)