vojtamolda/reinforcement-learning-an-introduction
Jupyter notebook solutions to exercises in the foundational reinforcement learning textbook by Sutton and Barto.
Velocity · 7d
+0.2
★ / day
Trend
→steady
star history
A repository containing solutions and implementations for exercises and programming problems from the classic RL textbook. The code uses Python 3, NumPy, and OpenAI Gym as the environment API. It covers tabular RL methods including multi-armed bandits, Q-learning, temporal-difference learning, and dynamic programming through code examples and accompanying PDF write-ups.