Skip to search formSkip to main contentSkip to account menu
Reinforcement Learning in Continuous Time and Space
  • K. Doya
  • Computer Science
    Neural Computation
  • 2000
This article presents a reinforcement learning framework for continuous-time dynamical systems without a priori discretization of time, state, and action. Basedonthe Hamilton-Jacobi-Bellman (HJB)…
View on MIT Press
A unifying computational framework for motor control and social interaction.
TLDR
The extent to which motor commands acting on the body can be equated with communicative signals acting on other people is examined and it is suggested that computational solutions for motor control may have been extended to the domain of social interaction.
View on PubMed
Parallel neural networks for learning sequential procedures
View on Elsevier
Complementary roles of basal ganglia and cerebellum in learning and motor control
  • K. Doya
  • Biology, Psychology
    Current Opinion in Neurobiology
  • 1 December 2000
View on Elsevier
Representation of Action-Specific Reward Values in the Striatum
TLDR
Representation of action values in the striatum is suggested, which can guide action selection in the basal ganglia circuit in monkeys who chose between left and right handle turns.
View on Publisher
What are the computations of the cerebellum, the basal ganglia and the cerebral cortex?
  • K. Doya
  • Biology, Psychology
    Neural Networks
  • 1 October 1999
View on PubMed
Metalearning and neuromodulation
  • K. Doya
  • Psychology, Biology
    Neural Networks
  • 1 June 2002
View on PubMed
Modulators of decision making
  • K. Doya
  • Biology, Psychology
    Nature Neuroscience
  • 1 April 2008
TLDR
This article aims to sort out factors that affect the process of decision making from the viewpoint of reinforcement learning theory and to bridge between such computational needs and their neurophysiological substrates.
View on Nature
Multiple Model-Based Reinforcement Learning
TLDR
The basic idea is to decompose a complex task into multiple domains in space and time based on the predictability of the environmental dynamics to enable multiple model-based reinforcement learning for nonlinear, nonstationary control tasks.
View on MIT Press
Prediction of immediate and future rewards differentially recruits cortico-basal ganglia loops
TLDR
Brain mechanisms for reward prediction at different time scales in a Markov decision task and graded maps of time scale within the insula and the striatum suggest differential involvement of the cortico-basal ganglia loops in reward prediction in different time scale.
View on Springer
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License