arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.00549cs.CLcs.AI
收藏

在一个具有一致性发言者的交互世界中出现通信

Emergence of Communication in an Interactive World with Consistent Speakers

Tel Aviv University(特拉维夫大学)

Ben Bogin, Mor Geva, Jonathan Berant

摘要:

训练代理相互沟通,基于任务的监督只引起了相当大的关注,最近,由于越来越多的兴趣,开发模型的人与代理的互动。以前的工作集中在简单的环境中,训练使用策略梯度是可行的,尽管在训练过程中的代理的非平稳性。在本文中,我们提出了一个更具挑战性的环境来测试从原始像素通信的出现,其中使用策略梯度训练失败。我们提出了一种新的模型和训练算法,该算法利用学习的表示空间的结构在训练的初始阶段产生更一致的说话人,从而稳定学习。我们的经验表明,我们的算法大大提高了性能相比,策略梯度。我们还提出了一个新的基于约束的度量标准,用于测量出现的通信中的上下文独立性,并发现我们的方法相比于策略梯度和其他竞争基线增加了上下文独立性。

英文摘要:

Training agents to communicate with one another given task-based supervision only has attracted considerable attention recently, due to the growing interest in developing models for human-agent interaction. Prior work on the topic focused on simple environments, where training using policy gradient was feasible despite the non-stationarity of the agents during training. In this paper, we present a more challenging environment for testing the emergence of communication from raw pixels, where training using policy gradient fails. We propose a new model and training algorithm, that utilizes the structure of a learned representation space to produce more consistent speakers at the initial phases of training, which stabilizes learning. We empirically show that our algorithm substantially improves performance compared to policy gradient. We also propose a new alignment-based metric for measuring context-independence in emerged communication and find our method increases context-independence compared to policy gradient and other competitive baselines.

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。

↑