KnowRU: Knowledge Reusing via Knowledge Distillation in Multi-agent Reinforcement Learning

03/27/2021
by   Zijian Gao, et al.
0

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.

READ FULL TEXT

page 8

page 12

page 13

page 15

page 17

research
05/25/2021

KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning

Recently, deep reinforcement learning (RL) algorithms have made great pr...
research
01/18/2022

K-nearest Multi-agent Deep Reinforcement Learning for Collaborative Tasks with a Variable Number of Agents

Traditionally, the performance of multi-agent deep reinforcement learnin...
research
03/18/2021

Human-Inspired Multi-Agent Navigation using Knowledge Distillation

Despite significant advancements in the field of multi-agent navigation,...
research
05/29/2023

Privileged Knowledge Distillation for Sim-to-Real Policy Generalization

Reinforcement Learning (RL) has recently achieved remarkable success in ...
research
02/01/2020

Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning

Off-policy ensemble reinforcement learning (RL) methods have demonstrate...
research
07/05/2022

The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions

In this paper, we propose a novel benchmark called the StarCraft Multi-A...
research
02/27/2021

Multi-agent Reinforcement Learning in OpenSpiel: A Reproduction Report

In this report, we present results reproductions for several core algori...

Please sign up or login with your details

Forgot password? Click here to reset