Quantifying Reinforcement-Learning Agent’s Autonomy, Reliance on Memory and Internalisation of the Environment

Quantifying Reinforcement-Learning Agent’s Autonomy, Reliance on Memory and Internalisation of the Environment

Intuitively, the level of autonomy of an agent is related to the degree to which the agent’s goals and behaviour are decoupled from the immediate control by the environment. Here, we capitalise on a recent information-theoretic formulation of autonomy and introduce an algorithm for calculating auton...

Full description

Bibliographic Details
Main Authors: Anti Ingel, Abdullah Makkeh, Oriol Corcoll, Raul Vicente
Format: Article
Language:English
Published: MDPI AG 2022-03-01
Series:Entropy
Subjects:
autonomy
reinforcement learning
information theory
partial information decomposition
non-trivial informational closure
deep learning
Online Access:https://www.mdpi.com/1099-4300/24/3/401

Internet

https://www.mdpi.com/1099-4300/24/3/401

Similar Items