The Power of Teams that Disagree: Team Formation in Large Action Spaces.
Leandro Soriano MarcolinoHaifeng XuAlbert Xin JiangMilind TambeEmma BowringPublished in: COIN@AAMAS/PRICAI (2014)
Keyphrases
- team formation
- action space
- multi agent
- state space
- markov decision processes
- continuous state
- reinforcement learning
- single agent
- real valued
- state and action spaces
- stochastic processes
- skill learning
- continuous action
- distributed network
- control policies
- partially observable markov decision processes
- robot navigation