Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop
- Submitting institution
-
University of Hertfordshire
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 20209964
- Type
- D - Journal article
- DOI
-
10.3389/fnbot.2018.00045
- Title of journal
- Frontiers in Neurorobotics
- Article number
- 45
- First page
- 45
- Volume
- 12
- Issue
- AUG
- ISSN
- 1662-5218
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- For the first time, unification, in a coherent formalism, of several information-theoretic intrinsic motivation formalisms, Friston’s Free Energy Formalism, empowerment, predictive information, inside a framework of active inference, including links to Universal Reinforcement Learning of Hutter. Starting point of several investigations exploring the consequences of these links between the various models. Cited by papers of Karl Friston (UCL) and Jan Peters (TU Darmstadt), triggered collaboration with Rosas (Imperial) and Mediano (Cambridge), with first publication on Causal Blankets (2020) and joint proposal submission to Templeton. Collaboration ongoing.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -