2026/08/04 by Matteo Morini, Pietro Terna
Computer Science · #cs.SI
published as M. Morini, and P. Terna (2021). A note on reinforcement learning to develop self-defined agents' behavior. Carlo Alberto Notebooks, No. 638, January 2021
arxiv created 2026/08/04 · arxiv updated 2026/08/05
The key point in this note is the self-development of simple behavior strategies, consistently with the bounded rationality hypothesis. Our artificial agents adopt learning techniques, mainly unsupervised, to achieve internal consistency in their behavior, with unexpected results. Those results can be considered mainly as the effects of the observer interpretation. The first technique in use has the name Cross Targets: to train the learning agent we use data crossed between the guesses about the action to be done and the guesses about the following results. An application of the CT "blind" strategy development is then presented: random walkers solve a node classification problem on a graph, after having learnt how to remain in homogeneous regions.