Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning.
Mehdi DadvarRashmeet Kaur NayyarSiddharth SrivastavaPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning problems
- supervised learning
- higher level
- unsupervised learning
- temporal difference learning
- state space
- online learning
- learning systems
- inductive inference
- temporal difference
- evolutionary learning
- multiple representations
- learning capabilities
- action selection
- probabilistic model
- dynamic programming
- active learning
- e learning