A One-shot Convex Optimization Approach to Risk-Averse Q-Learning.
Yuzhen HanMajid MazouchiSubramanya P. NageshraoHamidreza ModaresPublished in: CDC (2021)
Keyphrases
- convex optimization
- risk averse
- risk neutral
- reinforcement learning
- utility function
- decision makers
- stochastic programming
- function approximation
- state space
- learning algorithm
- optimal policy
- total variation
- low rank
- model free
- primal dual
- portfolio management
- convex optimization problems
- convex relaxation
- multistage
- image restoration
- expected utility
- infinite horizon
- image processing
- decision making