Learning in Sparse Rewards settings through Quality-Diversity algorithms.
Giuseppe PaoloPublished in: CoRR (2022)
Keyphrases
- learning algorithm
- noise tolerant
- reinforcement learning
- computational complexity
- neural network
- supervised learning
- computational cost
- knowledge acquisition
- learning analytics
- data structure
- bandit problems
- learning process
- learning tasks
- computationally efficient
- machine learning
- learning systems
- sparse data
- inductive inference
- dictionary learning
- online learning
- poor quality
- multi armed bandits
- machine learning algorithms
- theoretical analysis
- labeled data
- multi objective
- significant improvement
- prior knowledge
- evolutionary algorithm
- learning environment
- high quality
- data mining