Is the Cerebellum a Model-Based Reinforcement Learning Agent?

Bharath Masetty, Reuth Mirsky, Ashish Deshpande, Michael Mauk, Peter Stone

Research output: Contribution to conferencePaperpeer-review

2 Scopus citations


The cerebellum is an integral part of the human brain and understanding its role in learning might present an opportunity for reciprocal enrichment of the fields of artificial intelligence and neuroscience. In this paper, we present a novel idea that the cerebellum's role goes beyond functioning as a supervised learning machine to performing model-based reinforcement learning. We revisit the current theories about the cerebellum's role in human learning processes and propose a novel way of evaluating it in the context of the simulated cerebellum. Based on the recent experimental findings, we propose that the cerebellum performs modelbased reinforcement learning and we propose a way to evaluate the hypothesis using a simulated cerebellum. Finally, we discuss the necessary conditions to evaluate the hypothesis and the potential implications for future research of the hypothesis holds.

Original languageEnglish
StatePublished - 2021
Externally publishedYes
EventAdaptive and Learning Agents Workshop, ALA 2021 at AAMAS 2021 - Virtual, Online, United Kingdom
Duration: 3 May 20214 May 2021


ConferenceAdaptive and Learning Agents Workshop, ALA 2021 at AAMAS 2021
Country/TerritoryUnited Kingdom
CityVirtual, Online

Bibliographical note

Publisher Copyright:
© 2021 Association for Computing Machinery.


  • Cerebellum
  • Forward models
  • Neuroscience
  • Reinforcement learning
  • Reward function


Dive into the research topics of 'Is the Cerebellum a Model-Based Reinforcement Learning Agent?'. Together they form a unique fingerprint.

Cite this