Distributional reinforcement learning in the brain
By Adam S. Lowet, Qiao Zheng, Sara Matias, Jan Drugowitsch, Naoshige Uchida. 2020
66 citations recorded by the source corpus.
Learning about rewards and punishments is critical for survival. Classical studies have demonstrated an impressive correspondence between the firing of dopamine neurons in the mammalian midbrain and the reward prediction errors of reinforcement learning algorithms, which express the difference between actual reward and predicted mean reward. However, it may be advantageous to learn not only the mean but also the complete distribution of potential rewards. Recent advances in machine learning have revealed a biologically plausible set of algorithms for reconstructing this reward distribution from experience. Here, we review the mathematical foundations of these algorithms as well as initial evidence for their neurobiological implementation. We conclude by highlighting outstanding questions regarding the circuit computation and behavioral readout of these distributional codes.
Subfields: Artificial Intelligence, Cognitive Neuroscience
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Matthew Riemer
- Irina Rish
- Khimya Khetarpal
- Doina Precup
- Sergey Levine
- Joelle Pineau
- Eric Eaton
- Chelsea Finn
In Cognitive Neuroscience
Citations in the corpus
- Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “For example, there is significant evidence in the literature that human learning is either uncertainty-aware or Bayesian in nature (Niv et al., 2005; Fleming and Daw, 2017; Babayan et al., 2018; Lowet et al., 2020).”