Metrics and Continuity in Reinforcement Learning.
Charline Le LanMarc G. BellemarePablo Samuel CastroPublished in: AAAI (2021)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- robotic control
- reinforcement learning algorithms
- model free
- state space
- evaluation metrics
- multi agent
- relational reinforcement learning
- similarity metrics
- learning classifier systems
- dynamic programming
- learning process
- optimal policy
- information systems
- sufficient conditions
- social networks
- temporal difference
- software quality
- artificial intelligence
- partially observable
- markov decision process
- case study
- machine learning