Shaped Policy Search for Evolutionary Strategies using Waypoints.
Kiran LekkalaLaurent IttiPublished in: CoRR (2021)
Keyphrases
- policy search
- evolutionary strategy
- evolutionary algorithm
- reinforcement learning
- artificial immune system
- differential evolution
- constrained optimization
- evolutionary computation
- continuous state
- variable length
- multi objective optimization
- particle swarm optimization
- genetic algorithm
- dynamic programming
- ant colony optimization
- reinforcement learning algorithms
- particle swarm optimization pso
- mutation operator
- fitness function
- model free
- multi objective
- neural network
- policy gradient
- reward function
- machine learning
- markov decision processes
- markov decision problems
- computational intelligence
- learning algorithm
- robot navigation
- optimization problems
- metaheuristic