Learning to Coordinate via Quantum Entanglement in Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a novel framework for multi-agent reinforcement learning that leverages shared quantum entanglement to enable coordination strategies surpassing classical shared randomness, demonstrated through single-round and sequential decision-making tasks.

Contribution

It presents the first method to train MARL agents using shared quantum entanglement, including a differentiable policy parameterization and a quantum-aware policy architecture.

Findings

Learned strategies that achieve quantum advantage in black-box single-round games.

Demonstrated quantum advantage in multi-agent Dec-POMDP tasks.

Showed effectiveness of quantum coordination in experience-based training.

Abstract

The inability to communicate poses a major challenge to coordination in multi-agent reinforcement learning (MARL). Prior work has explored correlating local policies via shared randomness, sometimes in the form of a correlation device, as a mechanism to assist in decentralized decision-making. In contrast, this work introduces the first framework for training MARL agents to exploit shared quantum entanglement as a coordination resource, which permits a larger class of communication-free correlated policies than shared randomness alone. This is motivated by well-known results in quantum physics which posit that, for certain single-round cooperative games with no communication, shared quantum entanglement enables strategies that outperform those that only use shared randomness. In such cases, we say that there is quantum advantage. Our framework is based on a novel differentiable policy parameterization that enables optimization over quantum measurements, together with a novel policy architecture that decomposes joint policies into a quantum coordinator and decentralized local actors. To illustrate the effectiveness of our proposed method, we first show that we can learn, purely from experience, strategies that attain quantum advantage in single-round games that are treated as black box oracles. We then demonstrate how our machinery can learn policies with quantum advantage in an illustrative multi-agent sequential decision-making problem formulated as a decentralized partially observable Markov decision process (Dec-POMDP).