Combining Subgoal Graphs with Reinforcement Learning to Build a Rational Pathfinder.
Junjie ZengLong QinYue HuCong HuQuanjun YinPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- profit sharing
- graph theoretic
- dynamic programming
- machine learning
- graph theory
- partial order
- temporal difference
- series parallel
- optimal policy
- directed graph
- state space
- graph structure
- goal oriented
- neural network
- pattern recognition
- bipartite graph
- weighted graph
- learning process
- graph structures