A Bellman Optimality Equation for Plasticity

A theory of plasticity: capacity for change as inverse configurational constraint

Plasticity is invoked across the sciences to explain how systems can change, yet it is inferred from the very change it is meant to explain. A system may have many alternatives, realize none and still be plastic. Another may be driven far toward its only alternative, but the magnitude of that change does not establish...

Generalized Residual Closure: General Learning Dynamics for Stability-Plasticity Compatibility

Learning must acquire new capabilities while preserving both prior responsibilities and the capacity to learn again. We introduce Generalized Residual Closure (GRC), a framework for learning as recursive closure of future-relevant discrepancies: closing a residual establishes the conditions for subsequent prediction, i...

Energy-fed commitment: a minimal model of random selection followed by reinforcement

When a symmetric instability is crossed, fluctuations choose one of several equivalent branches. We study a minimal stochastic model of what can then make that choice progressively harder to undo. After selection, the stiffness of the selected state grows in proportion to the energy released each time the structure rec...

Evolutionary Recurrent Decision Model in Developing Adaptive and Maladaptive Behaviors

The results suggest that many psychopathology-relevant aspects may be interpreted as bounded cognitive systems operating under modern-ancestral environmental mismatch, positioning ERDM as a key computational cognitive tool that can be extended to other studies.

Towards Understanding the Impact of Plasticity Loss on Reinforcement Learning in Stochastic Environments

Continual Reinforcement Learning with Neuroevolution

Neuroevolution is established as a competitive alternative to RL under continual task changes, and it is suggested that training under perturbations in weight space may be a useful mechanism for continual learning more broadly.