Off-Policy Evolutionary Reinforcement Learning with Maximum Mutations.
Karush SuriPublished in: AAMAS (2022)
Keyphrases
- reinforcement learning
- evolutionary process
- genetic algorithm
- function approximation
- mutation rate
- evolutionary computation
- state space
- learning algorithm
- markov decision processes
- reinforcement learning algorithms
- evolutionary algorithm
- optimal policy
- evolutionary optimization
- real time
- temporal difference learning
- evolutionary search
- control policy
- policy search
- robotic control
- learning classifier systems
- maximum number
- optimal control
- learning strategies
- genetic programming
- computational intelligence
- multi objective
- active learning
- data mining