# Best Bandit Algorithms alternatives

Source: https://listme.name/alternatives/bandit-algorithms

1. **Reinforcement Learning: An Introduction** (score 94.0): Standard reinforcement learning textbook by Sutton and Barto with a free PDF. Free | PDF/Print. https://listme.name/books/reinforcement-learning-an-introduction
2. **Reinforcement Learning and Optimal Control** (score 90.5): Bertsekas on reinforcement learning as dynamic programming, free PDF. Free | PDF. https://listme.name/books/reinforcement-learning-and-optimal-control
3. **TinyML** (score 89.0): Practical guide to running machine learning on microcontrollers. Paid | PDF/Print. https://listme.name/books/tinyml-book
4. **Efficient Processing of Deep Neural Networks** (score 87.5): Hardware-focused book on running deep neural networks efficiently. Paid | PDF/Print. https://listme.name/books/efficient-processing-of-deep-neural-networks
5. **Reinforcement Learning: Theory and Algorithms** (score 86.0): Theory-first reinforcement learning textbook with a free, frequently updated PDF. Free | PDF. https://listme.name/books/reinforcement-learning-theory-and-algorithms
6. **Foundations of Deep Reinforcement Learning** (score 85.0): Theory and Python practice for deep reinforcement learning. Paid | Print. https://listme.name/books/foundations-of-deep-reinforcement-learning
7. **Algorithms for Reinforcement Learning** (score 84.5): Short 2010 reinforcement learning algorithms book with a free PDF. Free | PDF/Print. https://listme.name/books/algorithms-for-reinforcement-learning
8. **Fringe Learning: Resource-Efficient RL for Edge ML*** (score 79.5): Guide to reinforcement learning on microcontrollers and NPUs. One-time purchase | PDF. https://listme.name/books/fringe-learning
9. **Grokking Deep Reinforcement Learning** (score 83.0): Practical introduction to deep reinforcement learning with exercises. Paid | Print. https://listme.name/books/grokking-deep-reinforcement-learning

\* Made by, or connected to, the publisher of listme.name. Listed on the same criteria, with the lift described at https://listme.name/methodology and https://listme.name/disclosure.