Keyphrases
- reinforcement learning
- learning algorithm
- noise tolerant
- learning process
- online learning
- reinforcement learning methods
- learning agent
- multi armed bandit
- machine learning
- bandit problems
- inverse reinforcement learning
- learning tasks
- active learning
- learning models
- machine learning algorithms
- worst case
- supervised learning
- learning problems
- learning classifier systems
- reward function
- function approximators
- decision makers
- rl algorithms
- autonomous learning
- lower bound