method · first seen 7 Oct 2026
multichain Markov decision process
Markov decision process in which policies may induce multiple recurrent classes with different long-run behaviour.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Average-Reward Reinforcement Learning for Multichain MDPs: A Hierarchical Decomposition ApproachPapers · 7 Oct 2026 · Huizhen Yu, Isaiah Heidt
Latest sources
- Average-Reward Reinforcement Learning for Multichain MDPs: A Hierarchical Decomposition ApproachPapers · 7 Oct 2026 · Huizhen Yu, Isaiah Heidt