Rethinking Population-assisted Off-policy Reinforcement Learning.
Bowen ZhengRan ChengPublished in: GECCO (2023)
Keyphrases
- reinforcement learning
- model free
- function approximation
- markov decision processes
- optimal policy
- population size
- temporal difference
- state space
- cultural algorithms
- relational reinforcement learning
- multi agent reinforcement learning
- reinforcement learning algorithms
- neural network
- supervised learning
- learning process
- learning algorithm
- robotic control
- optimal control
- database
- technology enhanced learning
- direct policy search
- search algorithm
- autonomous learning
- markov decision process
- temporal difference learning
- mutation operator
- robot control
- control problems
- partially observable
- multi objective
- multi agent
- information retrieval
- real time