Discovering Individual Rewards in Collective Behavior through Inverse Multi-Agent Reinforcement Learning.
Daniel WälchliPascal WeberPetros KoumoutsakosPublished in: CoRR (2023)
Keyphrases
- multi agent reinforcement learning
- collective behavior
- reinforcement learning
- swarm intelligence
- multi agent
- social behavior
- stochastic games
- learning algorithm
- markov decision processes
- neural network
- learning agents
- social media
- multi agent systems
- information flow
- physical world
- computer vision
- social networks
- genetic algorithm
- machine learning
- multi agent learning
- real time