Generalized attention-weighted reinforcement learning.
Lennart BramlageAurelio CortesePublished in: Neural Networks (2022)
Keyphrases
- reinforcement learning
- state space
- dynamic programming
- markov decision processes
- autonomous mental development
- machine learning
- multi agent
- optimal policy
- visual attention
- model free
- learning problems
- multi agent reinforcement learning
- action space
- learning capabilities
- reinforcement learning algorithms
- weighted sum
- function approximation
- real world
- objective function
- data mining