- How can we get Q*?
- Monte-carlo
https://youtu.be/bCifW0SENGs?si=-Brm4lwVPN4emAG2
- Temporal Difference
- 1 Step Temporal Difference
- Incremental Monte Carlo Updates
- Time Difference
- Temporal Difference Error
- Temporal Difference Target
https://youtu.be/vfLrBPYwuFA?si=zTnAFh5bjHerEKX-
- SARSA
https://youtu.be/vfLrBPYwuFA?si=zTnAFh5bjHerEKX-
- Monte-carlo VS Temporal Difference