Intermittent Absence of Control during Reinforcement Learning Interferes with Pavlovian Bias in Action Selection.
Gábor CsifcsákEirik MelsæterMatthias MittnerPublished in: J. Cogn. Neurosci. (2020)
Keyphrases
- action selection
- reinforcement learning
- temporal difference
- basal ganglia
- robot soccer
- control problems
- action space
- decision making
- continuous state and action spaces
- human robot
- function approximation
- optimal control
- robot control
- machine learning
- multi agent
- action selection mechanism
- adaptive control
- model free
- control policy
- state action
- control policies