no code implementations • 2 Feb 2023 • Dmytro Grytskyy, Jorge Ramírez-Ruiz, Rubén Moreno-Bote
Previous work has separately addressed different forms of action, state and action-state entropy regularization, pure exploration and space occupation.
1 code implementation • 20 May 2022 • Jorge Ramírez-Ruiz, Dmytro Grytskyy, Chiara Mastrogiuseppe, Yamen Habib, Rubén Moreno-Bote
Most theories of behavior posit that agents tend to maximize some form of reward or utility.
no code implementations • 11 Mar 2021 • Dmytro Grytskyy, Renaud B. Jolivet
We then applied gradient descent for a combination of mutual information and energetic costs to obtain a learning rule.