A Policy Gradient Algorithm to Alleviate the Multi-Agent Value Overestimation Problem in Complex Environments

Abstract

Multi-agent reinforcement learning excels at addressing group intelligent decision-making problems involving sequential decision-making. In particular, in complex, high-dimensional state and action spaces, it imposes higher demands on the reliability, stability, and adaptability of decision algorithms. The reinforcement learning algorithm based on the multi-agent deep strategy gradient incorporates a function approximation method using discriminant networks. However, this can lead to estimation errors when agents evaluate action values, thereby reducing model reliability and stability and resulting in challenging convergence. With the increasing complexity of the environment, there is a decline in the quality of experience collected by the experience playback pool, resulting in low efficiency of the sampling stage and difficulties in algorithm convergence. To address these challenges, we propose an innovative approach called the empirical clustering layer-based multi-agent dual dueling policy gradient (ECL-MAD3PG) algorithm. Experimental results demonstrate that our ECL-MAD3PG algorithm outperforms other methods in various complex environments, demonstrating a remarkable 9.1% improvement in mission completion compared to MADDPG within the context of complex UAV cooperative combat scenarios.