MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning.
DiJia SuJason D. LeeJohn M. MulveyH. Vincent PoorPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- partial observability
- risk minimization
- optimization problems
- computationally expensive
- concave convex procedure
- robust optimization
- learning problems
- neural network
- markov decision processes
- optimization algorithm
- machine learning
- combinatorial optimization
- computationally efficient
- function approximation
- optimization process
- reinforcement learning algorithms
- evolutionary algorithm
- support vector
- learning algorithm