Softwares

Please let me know if you have questions. Email: ddyuudd [at] gmail [dot] com

• Finding Options for Planning and Reinforcement Learning
  • Option discovery algorithms for planning and reinforcement learning CODE
• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
  • Neural Architecture Search (NAS) with Monte Carlo Tree Search. CODE
• Parallel Best-First Search
  • Hash Distributed A* for a classical planner built on top of fast-downward planner (MPI) CODE
  • Parallel best-first search algorithms for domain-specific solvers: sliding-tile, grid-pathfinding, and multiple sequence alignment (pthread) CODE
  • Hash Distributed A* for domain-specific solvers optimized for HDA* (pthread) CODE (note: This code base is under refactoring.)
  • Instance generators and generated instances for (15-puzzle, 24-puzzle, grid-pathfinding, traveling salesperson problem, multiple sequence alignment) CODE
• Dominated Action Sequence Detection (Atari)
  • Dominated action sequence detection implemented to blind search for Arcade Learning Environment (Atari) CODE
• Transfer in Lifelong Reinforcement Learning
  • Q-learning, RMax, Delayed Q-learning with transfer in Lifelong Reinforcement Learning CODE
  • Lipschitz Lifelong Reinforcement Learning CODE