Swarm Intelligence in Cooperative Environments: n-Step Dynamic Tree Search Algorithm Overview

Reinforcement learning tree-based planningmethods have been gaining popularity in the last few years due to their success in single-agent domains,where a perfect simulatormodel is available: for example,Go and chess strategic board games. This paper pretends to extend tree search algorithms to the multiagent setting in a decentralized structure, dealing with scalability issues and exponential growth of computational resources. The n-step dynamic tree search combines forward planning and direct temporal-difference updates, outperforming markedly conventional tabular algorithms such asQ learning and state-action-reward-state-action (SARSA). Future state transitions and rewards are predicted with a model built and learned from real interactions between agents and the environment. This paper analyzes the developed algorithmin the hunter–pursuit cooperative game against stochastic and intelligent evaders.The n-step dynamic tree search aims to adapt single-agent tree search learningmethods to themultiagent boundaries and is demonstrated to be a remarkable advance as compared to conventional temporal-difference techniques.