KnowRU: Knowledge Reusing via Knowledge Distillation in Multi-agent Reinforcement Learning
This addresses the challenge of efficient training in multi-agent systems, but it is incremental as it builds on existing knowledge distillation techniques.
The authors tackled the problem of time-consuming and resource-intensive training in multi-agent reinforcement learning by proposing KnowRU, a knowledge reusing method via knowledge distillation, which accelerates training for new tasks and improves asymptotic performance, as shown in experiments outperforming recent methods.
Recently, deep Reinforcement Learning (RL) algorithms have achieved dramatically progress in the multi-agent area. However, training the increasingly complex tasks would be time-consuming and resources-exhausting. To alleviate this problem, efficient leveraging the historical experience is essential, which is under-explored in previous studies as most of the exiting methods may fail to achieve this goal in a continuously variational system due to their complicated design and environmental dynamics. In this paper, we propose a method, named "KnowRU" for knowledge reusing which can be easily deployed in the majority of the multi-agent reinforcement learning algorithms without complicated hand-coded design. We employ the knowledge distillation paradigm to transfer the knowledge among agents with the goal to accelerate the training phase for new tasks, while improving the asymptotic performance of agents. To empirically demonstrate the robustness and effectiveness of KnowRU, we perform extensive experiments on state-of-the-art multi-agent reinforcement learning (MARL) algorithms on collaborative and competitive scenarios. The results show that KnowRU can outperform the recently reported methods, which emphasizes the importance of the proposed knowledge reusing for MARL.