SOURCE-LINKED INTELLIGENCE

Adaptive Agent Design

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

We consider an agent acting against a general non-Markovian environment. The agent maintains its agent states, but is free to choose a transition kernel across those states and optimize its state-feedback control policies. We study the bi-level agent design problem that optimizes the transition kernel and the policy it induces, given said kernel with offline data of observations and actions obtained via a behavioral policy. For general environments, we show that a soft $Q$-learning algorithm converges almost surely to the fixed point of a soft Bellman equation defined by the stationary average

Read original source ↗ Open in workspace

recordType

paper

region

Global