EVO-RL: Evolutionary-Driven Reinforcement Learning.
Ahmed HallawaThorsten BornAnke SchmeinkGuido DartmannArne PeineLukas MartinGiovanni IaccaA. E. EibenGerd AscheidPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- model free
- markov decision processes
- evolutionary computation
- learning algorithm
- control problems
- data driven
- genetic algorithm
- rl algorithms
- temporal difference
- transfer learning
- reinforcement learning methods
- learning process
- action space
- approximate dynamic programming
- autonomous learning
- learning agents
- optimal policy
- partially observable
- reward function
- partially observable domains
- markov decision process
- learning problems
- function approximators
- optimal control
- supervised learning
- machine learning
- direct policy search
- learning classifier systems
- continuous state
- learned knowledge
- control policy
- real robot
- multi agent