Primal-dual differential dynamic programming: A model-based reinforcement learning for constrained dynamic optimization.
Jong Woo KimTae Hoon OhSang Hwan SonJong Min LeePublished in: Comput. Chem. Eng. (2022)
Keyphrases
- primal dual
- dynamic optimization
- model based reinforcement learning
- dynamic programming
- linear programming
- markov decision processes
- linear program
- markov decision problems
- saddle point
- nature inspired
- semidefinite programming
- convex optimization
- convergence rate
- approximation algorithms
- reinforcement learning
- state space
- algorithm for linear programming
- optimal policy
- feasible solution
- metaheuristic
- search space
- policy iteration
- heuristic search
- optimal solution
- data mining