Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning.
Lingxiao WangZhuoran YangZhaoran WangPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- multi agent
- learning agents
- action selection
- multi agent systems
- single agent
- multi agent reinforcement learning
- multiagent systems
- intelligent agents
- multiagent learning
- software agents
- agent receives
- cooperative
- learning agent
- multiple agents
- state space
- markov random field
- autonomous agents
- multi agent environments
- markov decision processes
- high dimensional
- high dimensional data
- multiagent reinforcement learning
- decision making
- reinforcement learning agents
- dimensionality reduction
- optimal policy
- artificial agents
- objective function
- markov networks
- agent architecture
- evolutionary learning
- function approximation
- learning algorithm
- temporal difference
- model free
- robocup soccer
- agent learns
- machine learning
- reinforcement learning algorithms
- mobile agents
- belief networks
- graphical models
- maximum likelihood
- statistical mechanics
- vector space
- partial observability
- agent technology
- stochastic games
- learning capabilities