Hiking up that HILL with Cogment-Verse: Train & Operate Multi-agent Systems Learning from Humans | AAMAS 2023

This is the reference Cogment Verse paper, it was presented at the 22nd International Conference on Autonomous Agents and Multiagent Systems in May 2023 (AAMAS).

Further information about AIR’s presence at AAMAS 2023 are available in this blog post.
When using Cogment Verse in your research, please cite it.

Abstract

As more AI systems are deployed, humans are increasingly required to interact with them in multiple settings. However, such AI systems seldom learn from these interactions with humans, which provides an important opportunity to improve from human expertise and context awareness. Several recent results in the fields of reinforcement learning (RL) and human-in-the-loop learning (HILL) show that AI agents can perform better when humans are involved in their training process. Humans can provide rewards to the agent, demonstrate tasks, design curricula, or act directly in the environment, but these potential performance improvements also come with architectural, functional design, and engineering complexities. This paper discusses Cogment, a unifying open-source framework that introduces a formalism to support a variety of human(s)-agent(s) collaboration topologies and training approaches. Cogment addresses the complexity of training with humans within a production-ready platform. On top of Cogment, we introduce Cogment Verse a research platform dedicated to the research community to facilitate the implementation of HILL and Multi-Agent RL experiments. With these platforms, our end goal is to enable the generalization of intelligence ecosystems where AI agents and humans learn from each other and collaborate to address increasingly complex or sensitive use cases.

Cite

@inproceedings{cogment_verse_2023,
    title={
        Hiking up that HILL with Cogment-Verse: Train \& Operate Multi-agent Systems Learning from Humans
    },
    author={
        Gottipati, Sai Krishna and 
        Nguyen, Luong-Ha and 
        Mars, Clod{\'e}ric and 
        Taylor, Matthew E
    },
    booktitle={Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems},
    pages={3065--3067},
    year={2023}
}