Prioritized Guidance for Efficient Multi-Agent Reinforcement Learning Exploration
This work addresses slow learning and exploration challenges in MARL for cooperative multi-agent systems, representing an incremental improvement.
The paper tackles exploration inefficiency in multi-agent reinforcement learning (MARL) by introducing a novel communication method and predictive network to guide exploration and modify rewards, resulting in outperforming existing methods in cooperative environments.
Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less informative reward restricts the learning speed of MARL compared with the informative label in supervised learning. In this work, we leverage on a novel communication method to guide MARL to accelerate exploration and propose a predictive network to forecast the reward of current state-action pair and use the guidance learned by the predictive network to modify the reward function. An improved prioritized experience replay is employed to better take advantage of the different knowledge learned by different agents which utilizes Time-difference (TD) error more effectively. Experimental results demonstrates that the proposed algorithm outperforms existing methods in cooperative multi-agent environments. We remark that this algorithm can be extended to supervised learning to speed up its training.