Emergence of Collaborative Hunting via Multi-Agent Deep Reinforcement Learning.
Kazushi TsutsuiKazuya TakedaKeisuke FujiiPublished in: ICPR Workshops (1) (2022)
Keyphrases
- reinforcement learning
- multi agent
- agent societies
- cooperative
- state space
- reinforcement learning agents
- multi agent systems
- team formation
- multi agent reinforcement learning
- multiagent environments
- markov decision processes
- reinforcement learning algorithms
- collective intelligence
- single agent
- collaborative learning
- function approximation
- machine learning
- multi agent environments
- multiple agents
- learning algorithm
- supervised learning
- geographically dispersed
- optimal policy
- autonomous agents
- learning agents
- optimal control
- temporal difference
- coalition formation
- multi user
- control policy
- temporal difference learning
- partially observable
- knowledge sharing
- cooperative agents
- action selection
- data sets