AI RESEARCH
Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes
arXiv CS.LG
•
ArXi:2606.00427v1 Announce Type: new State abstraction in reinforcement learning is usually formulated as a partition of states based on reward and transition similarity. This excludes a common structural pattern in navigation, graph, and hierarchical decision problems: interface states such as doors, hubs, and bottlenecks naturally participate in than one region. We