Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning.
Matej JusupBarna PásztorTadeusz JanikKenan ZhangFrancesco CormanAndreas KrauseIlija BogunovicPublished in: AAMAS (2024)
Keyphrases
- reinforcement learning
- multi agent
- model free
- state space
- multi agent environments
- cooperative
- reinforcement learning algorithms
- markov random field
- function approximation
- single agent
- machine learning
- learning agents
- multiagent systems
- multi agent systems
- closed form
- reinforcement learning agents
- multi agent reinforcement learning
- traffic signal control
- markov networks
- bayesian inference
- em algorithm
- autonomous agents
- markov decision processes
- belief networks
- statistical mechanics
- learning algorithm
- variational methods
- temporal difference
- partially observable markov decision processes
- action selection
- reinforcement learning methods
- transfer learning
- team formation
- multiple agents
- multiagent reinforcement learning
- dynamic programming