Dynamic penalty function approach for constraints handling in reinforcement learning.
Haeun YooVictor M. ZavalaJay H. LeePublished in: CoRR (2020)
Keyphrases
- penalty function
- constrained optimization
- penalty functions
- reinforcement learning
- constrained optimization problems
- unconstrained optimization
- objective function
- real coded
- genetic algorithm
- constraint handling
- fitness function
- hard constraints
- multi agent
- saddle point
- dynamic environments
- lagrange multipliers
- markov decision processes
- state space
- learning algorithm
- machine learning
- optimal control
- function approximation
- neural network
- genetic programming
- multi objective