Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning.
Maxence FaldorFélix ChalumeauManon FlageatAntoine CullyPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- high quality
- higher quality
- machine learning
- function approximation
- multi agent
- object recognition
- keypoints
- state space
- learning problems
- computer vision
- data sets
- multi objective
- feature extraction
- information systems
- optimal control
- quality measures
- quality assessment
- model free
- temporal difference