21 citations · 42 across the 7 of their papers we have counts for
7 papers
Causal policy ranking
Daniel McNamee, Hana Chockler
Policies trained via reinforcement learning (RL) are often very complex even for simple tasks. In an episode with time steps, a policy will make decisions on actions to tak…
Transfer learning with causal counterfactual reasoning in Decision Transformers
Ayman Boustati, Hana Chockler, Daniel C. McNamee
The ability to adapt to changes in environmental contingencies is an important challenge in reinforcement learning. Indeed, transferring previously acquired knowledge to environmen…
Hierarchical model-based policy optimization: from actions to action sequences and back
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. The result…
Characterizing optimal hierarchical policy inference on graphs via non-equilibrium thermodynamics
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 contro…
Strong Homotopy Lie Algebras, Generalized Nahm Equations and Multiple M2-branes
Calin I. Lazaroiu, Daniel McNamee, Christian Saemann +1
We review various generalizations of the notion of Lie algebras, in particular those appearing in the recently proposed Bagger-Lambert-Gustavsson model, and study their interrelati…
Generalized Berezin-Toeplitz quantization of Kaehler supermanifolds
Calin Iuliu Lazaroiu, Daniel McNamee, Christian Saemann
We extend the construction of generalized Berezin and Berezin-Toeplitz quantization to the case of compact Hodge supermanifolds. Our approach is based on certain super-analogues of…