When "Your" reward is the same as "My" reward: Self-construal priming shifts neural responses to own vs. friends' rewards.
Michael E. W. VarnumZhenhao ShiAntao ChenJiang QiuShihui HanPublished in: NeuroImage (2014)
Keyphrases
- reinforcement learning
- bandit problems
- reward function
- expected reward
- neural network
- total reward
- state space
- multi armed bandits
- markov decision processes
- long run
- case study
- decision problems
- databases
- discounted reward
- neural fuzzy
- fitted q iteration
- policy gradient
- control policy
- network architecture
- biologically inspired
- search space
- expert systems
- multi agent
- learning algorithm
- machine learning