Decentralizing Multi-Agent Reinforcement Learning with Temporal Causal Information
By: Jan Corazza , Hadi Partovi Aria , Hyohun Kim and more
Potential Business Impact:
Helps robots and drones work together smarter.
Reinforcement learning (RL) algorithms can find an optimal policy for a single agent to accomplish a particular task. However, many real-world problems require multiple agents to collaborate in order to achieve a common goal. For example, a robot executing a task in a warehouse may require the assistance of a drone to retrieve items from high shelves. In Decentralized Multi-Agent RL (DMARL), agents learn independently and then combine their policies at execution time, but often must satisfy constraints on compatibility of local policies to ensure that they can achieve the global task when combined. In this paper, we study how providing high-level symbolic knowledge to agents can help address unique challenges of this setting, such as privacy constraints, communication limitations, and performance concerns. In particular, we extend the formal tools used to check the compatibility of local policies with the team task, making decentralized training with theoretical guarantees usable in more scenarios. Furthermore, we empirically demonstrate that symbolic knowledge about the temporal evolution of events in the environment can significantly expedite the learning process in DMARL.
Similar Papers
Explaining Decentralized Multi-Agent Reinforcement Learning Policies
Artificial Intelligence
Helps people understand how AI teams work together.
Strategic Coordination for Evolving Multi-agent Systems: A Hierarchical Reinforcement and Collective Learning Approach
Multiagent Systems
Helps robots work together better and smarter.
Multi-Agent Reinforcement Learning and Real-Time Decision-Making in Robotic Soccer for Virtual Environments
Robotics
Teaches robot soccer teams to play better together.