A stochastic maximum principle for risk-sensitive mean-field-type control.
Boualem DjehicheHamidou TembineRaúl TemponePublished in: CDC (2014)
Keyphrases
- risk sensitive
- optimal control
- control policies
- control strategies
- control strategy
- control policy
- markov decision processes
- control system
- utility function
- dynamic programming
- optimal policy
- motion control
- robot control
- markov decision chains
- stochastic optimization
- probabilistic model
- model free
- decision problems
- optimality criterion
- reinforcement learning