A deep reinforcement learning-based method applied for solving multi-agent defense and attack problems

Learning to cooperate among agents has always been an important research topic in artificial intelligence. Multiagent defense and attack, one of the important issues in multi-agent cooperation, requires multiple agents in the environment to learn effective strategies to achieve their goals. Deep reinforcement learning (DRL) algorithms have natural advantages dealing with continuous control problems especially under situations with dynamic interactions, and have provided new solutions for those long-studied multi-agent cooperation problems. In this paper, we start from deep deterministic policy gradient (DDPG) algorithm and then introduce multi-agent DDPG (MADDPG) to solve the multi-agent defense and attack problem under different situations. We reconstruct the considered environment, redefine the continuous state space, continuous action space, reward functions accordingly, and then apply deep reinforcement learning algorithms to obtain effective decision strategies. Several experiments considering different confrontation scenarios are conducted to validate the feasibility and effectiveness of the DRL-based methods. Experimental results show that through learning the agents can make better decisions, and learning with MADDPG achieves superior performance than learning with other DRL-based models, which also explains the importance and necessity of mastering other agents? information.

Automated summary

The paper discusses the important issue of multiagent defense and attack in the field of multi-agent cooperation, based on deep reinforcement learning algorithms, especially Multi-agent DDPG (MADDPG). By reconstructing and redefining the environment, experimental results show that learning with MADDPG can improve the decision-making abilities of agents better than other DRL models.