M^3RL: Mind-aware Multi-agent Management Reinforcement Learning.
Tianmin ShuYuandong TianPublished in: ICLR (Poster) (2019)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- state space
- reinforcement learning algorithms
- machine learning
- learning algorithm
- model free
- markov decision processes
- optimal policy
- management system
- artificial intelligence
- control problems
- temporal difference
- rl algorithms
- learning agents
- single agent
- dynamic programming
- multi agent environments
- information systems
- learning process
- cooperative
- intelligent agents
- action space
- data management
- policy search
- multi agent systems
- actor critic
- control policy
- temporal difference learning
- markov decision problems
- mental states
- reinforcement learning agents
- direct policy search
- state abstraction
- continuous state
- previously learned
- reinforcement learning methods
- markov decision process
- partially observable markov decision processes
- learning capabilities
- action selection
- multiple agents
- transfer learning
- supervised learning