(work in progress)
Swift replication for Sutton & Barto's book: Reinforcement Learning: An Introduction (2nd Edition).
Tested on macOS with Swift 5.3.2.
To run the code for a given chapter, execute swift run Chapter<N>.
| Chapter | Figures |
|---|---|
| 2: Multi-armed Bandits | 2.2, 2.3, 2.4, 2.5, 2.6 |
| 3: Finite Markov Decision Processes | 3.2, 3.5 |
| 4: Dynamic Programming | 4.1, 4.2, 4.3 |
| 5: Monte Carlo Methods | 5.1, 5.2, 5.3, 5.4 |
| 6: Temporal-Difference Learning | Ex 6.2, 6.2, Ex 6.5, Ex 6.6, 6.3, 6.5 |
