Emergence of belief-like representations through reinforcement learning.
Jay A. HennigSandra A. Romero PintoTakahiro YamaguchiScott W. LindermanNaoshige UchidaSamuel J. GershmanPublished in: PLoS Comput. Biol. (2023)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- state space
- real time
- belief functions
- dynamic programming
- belief revision
- reinforcement learning methods
- temporal difference learning
- function approximators
- small world
- belief state
- optimal policy
- genetic algorithm
- data sets
- case study
- decision making
- model free
- social networks
- probability theory
- partially observable
- learning algorithm
- neural network