arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.02157cs.AI
收藏

一种新的训练多个协作智能体的自动驾驶方法

A New Approach to Training Multiple Cooperative Agents for Autonomous Driving

Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学)

Ruiyang Yang, Siheng Li, Beihong Jin

摘要:

训练多个智能体在自动驾驶的复杂场景中执行安全和协作控制一直是一个挑战。对于一个小车队的汽车一起移动,本文提出了Lepus,一种新的方法来训练多个代理。Lepus采用纯合作的方式训练多个智能体,具有共享策略网络参数和共享多个智能体奖励函数的特点。特别是,Lepus通过对抗过程对策略网络进行预训练,提高了其协作决策能力,进一步提高了汽车驾驶的稳定性。此外,为了缓解稀疏奖励的问题,Lepus通过结合随机网络和蒸馏网络从专家轨迹中学习近似的奖励函数。我们在MADRaS仿真平台上进行了大量的实验。实验结果表明,Lepus训练的多个智能体可以避免碰撞尽可能多的同时驾驶,并优于其他四种方法,即DDPG-FDE,PSDDPG,MADDPG和MAGAIL(DDPG)的稳定性。

英文摘要:

Training multiple agents to perform safe and cooperative control in the complex scenarios of autonomous driving has been a challenge. For a small fleet of cars moving together, this paper proposes Lepus, a new approach to training multiple agents. Lepus adopts a pure cooperative manner for training multiple agents, featured with the shared parameters of policy networks and the shared reward function of multiple agents. In particular, Lepus pre-trains the policy networks via an adversarial process, improving its collaborative decision-making capability and further the stability of car driving. Moreover, for alleviating the problem of sparse rewards, Lepus learns an approximate reward function from expert trajectories by combining a random network and a distillation network. We conduct extensive experiments on the MADRaS simulation platform. The experimental results show that multiple agents trained by Lepus can avoid collisions as many as possible while driving simultaneously and outperform the other four methods, that is, DDPG-FDE, PSDDPG, MADDPG, and MAGAIL(DDPG) in terms of stability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑