Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations
This provides a tool for researchers and developers working on human-in-the-loop AI systems, though it is incremental as it builds on existing collaboration methods.
The paper tackles the architectural and engineering complexities of integrating humans into AI agent training by presenting Cogment, an open-source framework that supports various human-agent collaboration typologies and training approaches, offering scalable distributed solutions.
Involving humans directly for the benefit of AI agents' training is getting traction thanks to several advances in reinforcement learning and human-in-the-loop learning. Humans can provide rewards to the agent, demonstrate tasks, design a curriculum, or act in the environment, but these benefits also come with architectural, functional design and engineering complexities. We present Cogment, a unifying open-source framework that introduces an actor formalism to support a variety of humans-agents collaboration typologies and training approaches. It is also scalable out of the box thanks to a distributed micro service architecture, and offers solutions to the aforementioned complexities.