TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems.
Matteo GalliciMario MartinIvan MasmitjaPublished in: AAMAS (2023)
Keyphrases
- graph structure
- reinforcement learning problems
- multi agent
- reinforcement learning
- reinforcement learning algorithms
- reinforcement learning methods
- graphical models
- policy iteration
- single agent
- markov decision problems
- function approximators
- function approximation
- graph structures
- directed graph
- action space
- tree structure
- model free
- temporal difference
- state space
- multi agent systems
- multiple agents
- markov decision processes
- machine learning
- multiagent reinforcement learning
- undirected graph
- decision problems
- supervised learning
- least squares
- data structure
- learning algorithm