Distributed Multi-Agent Gradient Based Q-Learning with Linear Function Approximation.
Milos S. StankovicMarko BekoSrdjan S. StankovicPublished in: ECC (2024)
Keyphrases
- function approximation
- multi agent
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- model free
- cooperative
- temporal difference learning
- tile coding
- state action space
- temporal difference
- learning tasks
- radial basis function
- multi agent systems
- mountain car
- reinforcement learning algorithms
- single agent
- learning algorithm
- td learning
- reinforcement learning problems
- reinforcement learning methods
- real valued
- dynamic programming