Rethinking Population-assisted Off-policy Reinforcement Learning.
Bowen ZhengRan ChengPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- cultural algorithms
- population size
- markov decision processes
- reinforcement learning algorithms
- machine learning
- robotic control
- temporal difference learning
- optimal policy
- optimal control
- direct policy search
- learning process
- learning algorithm
- genetic algorithm
- action selection
- technology enhanced learning
- control problems
- active learning
- stochastic approximation
- pairwise