Learning Approximate and Exact Numeral Systems via Reinforcement Learning.
Emil CarlssonDevdatt P. DubhashiFredrik D. JohanssonPublished in: CogSci (2021)
Keyphrases
- reinforcement learning
- learning systems
- learning algorithm
- learning process
- learning agents
- prior knowledge
- active learning
- learning problems
- autonomous learning
- function approximation
- online learning
- management system
- computer systems
- optimal policy
- machine learning
- multi agent
- model free
- action selection
- temporal difference
- complex domains
- temporal difference learning
- state space
- evolutionary learning
- active exploration