dynamic programming
A method for solving complex problems by breaking them down into simpler subproblems, and storing their solutions to avoid redundant computations, commonly used in optimization and algorithm design.
- A Learning-Augmented Dynamic Programming Approach for Orienteering Problem with Time Windows
- DINGO: Constrained Inference for Diffusion LLMs
- Deep learning for continuous-time stochastic control with jumps
- Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
- Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems
- Multi-agent Markov Entanglement
- Preference-Based Dynamic Ranking Structure Recognition
- Reward-Aware Proto-Representations in Reinforcement Learning
- Structure Matters: Dynamic Policy Gradient
- \(\varepsilon\)-Optimally Solving Two-Player Zero-Sum POSGs