Deep Reinforcement Learning Aided Monte Carlo Tree Search for MIMO Detection

TL;DR

This paper introduces a novel MIMO detection method combining deep reinforcement learning with Monte Carlo tree search, leading to improved detection accuracy over traditional and DNN-based methods.

Contribution

It presents a new DRL-augmented MCTS detection algorithm for MIMO systems, integrating a custom policy-value network to enhance detection performance.

Findings

Significant performance improvements over original MCTS detection.

Favorable results compared to linear and DNN-based detection methods.

Effective under various channel conditions.

Abstract

This paper proposes a novel multiple-input multiple-output (MIMO) symbol detector that incorporates a deep reinforcement learning (DRL) agent into the Monte Carlo tree search (MCTS) detection algorithm. We first describe how the MCTS algorithm, used in many decision-making problems, is applied to the MIMO detection problem. Then, we introduce a self-designed deep reinforcement learning agent, consisting of a policy value network and a state value network, which is trained to detect MIMO symbols. The outputs of the trained networks are adopted into a modified MCTS detection algorithm to provide useful node statistics and facilitate enhanced tree search process. The resulted scheme, termed the DRL-MCTS detector, demonstrates significant improvements over the original MCTS detection algorithm and exhibits favorable performance compared to other existing linear and DNN-based detection methods under varying channel conditions.