Enhanced Deep Deterministic Policy Gradient Algorithm Using Grey Wolf Optimizer for Continuous Control Tasks.
Ebrahim Hamid Hasan SumieaSaid Jadid AbdulkadirMohammed Gamal RagabSafwan Mahmood Al-SelwiSuliamn Mohamed FatiAlawi AlqushaibiHitham AlhussianPublished in: IEEE Access (2023)
Keyphrases
- learning algorithm
- optimization algorithm
- policy gradient
- computational complexity
- objective function
- gradient ascent
- cost function
- control system
- search space
- convergence rate
- worst case
- np hard
- dynamic programming
- support vector machine svm
- multi agent systems
- monte carlo
- approximation methods
- optimal solution
- multi agent