Tag: cyclic

Provable Offline Reinforcement Learning for Structured Cyclic MDPs arXiv:2602.11679v1 Announce Type: new Abstract: We introduce a novel cyclic Markov decision process (MDP) framework for multi-step decision problems with heterogeneous stage-specific dynamics, transitions, and discount factors across the cycle. In this setting, offline learning is challenging: optimizing a policy at any stage shifts the state distributions…