1 code implementation • 21 Feb 2024 • Saul Santos, Vlad Niculae, Daniel McNamee, Andre F. T. Martins
Modern Hopfield networks have enjoyed recent interest due to their connection to attention in transformers.
no code implementations • 16 Nov 2021 • Daniel McNamee, Hana Chockler
Policies trained via reinforcement learning (RL) are often very complex even for simple tasks.
no code implementations • 28 Nov 2019 • Daniel McNamee
We develop a normative framework for hierarchical model-based policy optimization based on applying second-order methods in the space of all possible state-action paths.
no code implementations • 25 Sep 2019 • Daniel McNamee
We develop a normative theory of hierarchical model-based policy optimization for Markov decision processes resulting in a full-depth, full-width policy iteration algorithm.
no code implementations • 29 Dec 2017 • Daniel McNamee
Hierarchies are of fundamental interest in both stochastic optimal control and biological control due to their facilitation of a range of desirable computational traits in a control algorithm and the possibility that they may form a core principle of sensorimotor and cognitive control systems.
no code implementations • NeurIPS 2016 • Daniel McNamee, Daniel M. Wolpert, Mate Lengyel
Even in state-spaces of modest size, planning is plagued by the “curse of dimensionality”.