On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation

ArXi:2602.21424v2 Announce Type: replace-cross Reinforcement learning (RL) agents under partial observability often condition actions on internally accumulated information such as memory or inferred latent context. We formalise such information-conditioned interaction patterns as behavioural dependency: variation in action selection with respect to internal information under fixed observations. This induces a probe-relative notion of $\epsilon$-behavioural equivalence and a within-policy behavioural distance that quantifies probe sensitivity. We establish three structural results.