Continuous-time on-policy neural Reinforcement Learning of working memory tasks.
Davide ZambranoPieter R. RoelfsemaSander M. BohtéPublished in: IJCNN (2015)
Keyphrases
- working memory
- reinforcement learning
- prefrontal cortex
- cognitive load
- optimal policy
- basal ganglia
- action selection
- computational model
- state space
- functional connectivity
- information processing
- focus of attention
- long term memory
- transfer learning
- optimal control
- policy search
- cognitive architecture
- short term memory
- markov decision process
- working memory capacity
- individual differences
- neural network
- markov decision processes
- database
- learning styles
- dynamic programming
- learning process
- computer vision
- learning algorithm
- databases
- real time