Evolutionary Deep Reinforcement Learning via Hybridizing Estimation-of-Distribution Algorithms with Policy Gradients.
Thai Bao TranNgoc Hoang LuongPublished in: CEC (2024)
Keyphrases
- estimation of distribution algorithms
- reinforcement learning
- optimal policy
- evolutionary computation
- feature subset selection
- policy search
- action selection
- continuous domains
- evolutionary algorithm
- particle swarm optimization algorithm
- genetic algorithm
- multi objective optimization
- genetic programming
- multi objective
- particle swarm optimization
- markov decision processes
- function approximation
- combinatorial optimization
- combinatorial optimization problems
- function approximators
- dynamic programming
- state space
- reward function
- computational intelligence
- simulated annealing
- temporal difference
- learning algorithm
- machine learning
- graphical models