Extrinsic rewards, intrinsic rewards, and non-optimal behavior.
Mousa KarayanniIsrael NelkenPublished in: J. Comput. Neurosci. (2022)
Keyphrases
- reinforcement learning
- markov decision processes
- multiarmed bandit
- bandit problems
- camera calibration
- long term and short term
- control policy
- optimal design
- dynamic programming
- optimal control
- credit assignment
- behavior patterns
- reward function
- databases
- optimal solution
- geometric structure
- sufficient conditions
- worst case
- search algorithm
- total reward
- multiscale
- computer vision
- multi armed bandits
- data mining