Multi-objective Genetic Programming for Explainable Reinforcement Learning.
Mathurin VideauAlessandro LeiteOlivier TeytaudMarc SchoenauerPublished in: EuroGP (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- markov decision processes
- model free
- control problems
- robotic control
- transition model
- temporal difference
- optimal policy
- function approximators
- supervised learning
- state space
- learning agents
- temporal difference learning
- evolutionary learning
- partially observable domains
- database
- action selection
- transfer learning
- dynamic programming
- learning process
- search algorithm
- data mining
- neural network
- databases