Negotiating Team Formation Using Deep Reinforcement Learning.
Yoram BachrachRichard EverettEdward HughesAngeliki LazaridouJoel Z. LeiboMarc LanctotMichael JohansonWojciech M. CzarneckiThore GraepelPublished in: CoRR (2020)
Keyphrases
- team formation
- reinforcement learning
- multi agent
- american football
- function approximation
- software agents
- control problems
- dynamic programming
- learning algorithm
- model free
- state space
- temporal difference
- autonomous agents
- markov decision processes
- optimal policy
- cooperative
- reinforcement learning algorithms
- multiagent systems
- function approximators
- learning agents
- multi agent systems
- optimal control
- policy search
- website
- transition model
- automated negotiation
- machine learning
- action space
- deep learning
- robot control
- learning capabilities
- action selection
- supervised learning