The Dopaminergic Midbrain Mediates an Effect of Average Reward on Pavlovian Vigor.
Francesco RigoliBenjamin ChewPeter DayanRaymond J. DolanPublished in: J. Cogn. Neurosci. (2016)
Keyphrases
- average reward
- markov decision processes
- long run
- optimal policy
- semi markov decision processes
- reinforcement learning
- stochastic games
- optimality criterion
- policy iteration
- markov chain
- model free
- state action
- hierarchical reinforcement learning
- discounted reward
- data mining
- markov random field
- state space
- decision making
- learning algorithm