Practice of Course "Artificial Intelligence: Reinforcement Learning in Python" and *Advanced Course "Advanced AI: Deep Reinforcement Learning in Python"
-
Dynamic Programming
-
Monte Carlo
- Monte Carlo ES(Explore Start) - Crazy Grid World.ipynb
-
Temporal Differences
- SARSA - Crazy Grid World.ipynb
- Q Learning - Crazy Grid World.ipynb
-
Approximation Methods
- Approx Semigradient SARSA Control - Crazy Grid World.ipynb
-
Temporal Differences
- SARSA - QTable + Bins
- Q Learning - QTable + Bins
-
Approximation Methods
- Approx SemiGrad SARSA Control