231 citations · 686 across the 18 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2020★ 2 cited
Reward Maximisation through Discrete Active Inference
Lancelot Da Costa, Noor Sajid, Thomas Parr +2
Active inference is a probabilistic framework for modelling the behaviour of biological and artificial agents, which derives from the principle of minimising free energy. In recent…
cs.AI2020★ 23 cited
Action and Perception as Divergence Minimization
Danijar Hafner, Pedro A. Ortega, Jimmy Ba +3
To learn directed behaviors in complex environments, intelligent agents need to optimize objective functions. Various objectives are known for designing artificial agents, includin…