Abstract. In multi-agent reinforcement learning systems, it is important to share a reward among all agents. We focus on the Rationality Theorem of Profit Sharing [5] and analyze ...
The ability to generate narrative is of importance to computer systems that wish to use story effectively for entertainment, training, or education. We identify two properties of ...
A major challenge for traditional approaches to multiagent learning is to train teams that easily scale to include additional agents. The problem is that such approaches typically...
David B. D'Ambrosio, Joel Lehman, Sebastian Risi, ...
This paper describes a probabilistic syntactic approach to the detection and recognition of temporally extended activities and interactions between multiple agents. A complete sys...
This paper presents a stochastic multi-agent model of stock market. The market dynamics include switches between chartists and fundamentalists and switches in the prevailing opinio...