Classical Planning & Search Algorithms Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Search is the substrate of intelligence, from A* on grids to Monte Carlo tree search in Go. These classic papers distill the heuristics, sampling, and planning ideas that still power modern AI systems.

Classical Planning & Search Algorithms: 10 key papers

1. Value Iteration Networks
   Tamar et al. arXiv 2016.
2. The Predictron: End-To-End Learning and Planning
   Silver et al. arXiv 2016.
3. Universal Planning Networks
   Srinivas et al. arXiv 2018.
4. Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees
   Chen et al. arXiv 2019.
5. Neural Algorithmic Reasoning
   Veličković and Blundell. arXiv 2021.
6. Discrete Sequential Prediction of Continuous Actions for Deep RL
   Metz et al. arXiv 2017.
7. Bridging Hamilton-Jacobi Safety Analysis and Reinforcement Learning
   Fisac et al. 2019.
8. Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization
   Cappart et al. arXiv 2020.
9. Value Prediction Network
   Oh et al. arXiv 2017.
10. TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
    Farquhar et al. arXiv 2017.

Related reading lists

• Monte Carlo Tree Search
• Goal-Conditioned Reinforcement Learning
• Neural Architecture Search
• World Models and Model-Based RL
• Model-Based Reinforcement Learning
• AI Alignment & Safety
• Curiosity-Driven Exploration
• Quality-Diversity & Novelty Search