ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward.
Zixian MaRose WangLi Fei-FeiMichael S. BernsteinRanjay KrishnaPublished in: CoRR (2022)
Keyphrases
- multi agent
- reinforcement learning
- multi agent systems
- long run
- cooperative
- intelligent agents
- multiple agents
- image alignment
- autonomous agents
- dynamic time warping
- multiagent systems
- single agent
- software agents
- reward function
- agent oriented
- agent communication
- procrustes analysis
- american football
- multi agent environments
- team formation
- ontology matching
- sequence alignment
- genetic algorithm
- distance measure
- state space