rlai-exercises and rl-sandbox
These are competitors—both provide exercise solutions and algorithm implementations from the same Sutton & Barto textbook, targeting the same learning use case without meaningful differentiation in scope or approach.
About rlai-exercises
iamhectorotero/rlai-exercises
Exercise Solutions for Reinforcement Learning: An Introduction [2nd Edition]
Implements solutions across foundational RL concepts including multi-armed bandits, Markov decision processes, dynamic programming, and temporal difference learning. Solutions combine mathematical derivations with Python implementations of core algorithms like Q-learning and policy gradient methods. Designed as a companion resource to validate understanding against the textbook's theoretical frameworks and exercises.
About rl-sandbox
ocraft/rl-sandbox
Selected algorithms and exercises from the book Sutton, R. S. & Barton, A.: Reinforcement Learning: An Introduction. 2nd Edition, MIT Press, Cambridge, 2018.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work