The risks and rewards of conditioning noncooperative designs to additional information.
Dario PaccagnanJason R. MardenPublished in: Allerton (2017)
Keyphrases
- reinforcement learning
- decision making
- markov decision processes
- multiarmed bandit
- bandit problems
- risk factors
- risk management
- multi armed bandits
- data sets
- risk assessment
- design principles
- multi agent systems
- design space
- risk analysis
- database systems
- credit assignment
- condition numbers
- image processing
- neural network