Abstract
Reinforcement learning, optimization, and planning/search are interconnected domains in artificial intelligence. Algorithms within these domains share many similarities. They complement each other in solving complex decision-making problems, and also offer opportunities for cross-disciplinary integration. However, conducting research on algorithms across these domains typically requires learning the specialized libraries. These libraries often couple algorithms with domain-specific problem classes, making it difficult to conduct cross-disciplinary researches. In order to solve this problem, we developed a generic and lightweight framework for reinforcement learning, optimization, and planning/search algorithms (RLOP). It implements only the core logic of algorithms, abstracting away domain-specific details by defining interface functions, which enables flexible customization and efficient integration across different domains. The framework has been open-sourced at https://github.com/songzhg/RLOP.
Keywords
- Machine Learning: ML: Reinforcement learning
- Search: S: Search and machine learning
- Planning and Scheduling: PS: Search in planning and scheduling
- Search: S: Combinatorial search and optimisation
- Planning and Scheduling: PS: Planning algorithms
- Search: S: Heuristic search
- Search: S: Local search
- Multidisciplinary Topics and Applications: MDA: Computer games
- Planning and Scheduling: PS: Routing
- Search: S: Game playing
- Constraint Satisfaction and Optimization: CSO: Solvers and tools
- Planning and Scheduling: PS: Markov decisions processes
