Distributed consensus-based multi-agent temporal-difference learning.
Milos S. StankovicMarko BekoSrdjan S. StankovicPublished in: Autom. (2023)
Keyphrases
- multi agent
- temporal difference learning
- reinforcement learning
- fixed point
- function approximation
- approximate value iteration
- game playing
- evaluation function
- temporal difference
- reinforcement learning algorithms
- multi agent systems
- markov decision process
- model selection
- monte carlo
- graphical models
- state space
- multiple agents
- pairwise