Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations

2021/06/21 by AI Redefined, Sai Krishna Gottipati, Redefined, AI +9 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #D.2.11 #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #I.2 #I.2.11 #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #cs.AI #cs.HC #cs.LG #cs.MA

paper · pdf · doi:10.48550/arxiv.2106.11345

16 pages, 7 figures

arxiv created 2021/06/21 · arxiv updated 2021/06/23

Abstract

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.

Cited by

• A Systematic Approach to Design Real-World Human-in-the-Loop Deep Reinforcement Learning: Salient Features, Challenges and Trade-offs

Related

• Human and Multi-Agent collaboration in a human-MARL teaming framework
• An Interactive Agent Foundation Model
• Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration
• HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning
• The Human-AI Handshake Framework: A Bidirectional Approach to Human-AI Collaboration