arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.06370cs.CLcs.AIcs.LG
收藏

面向任务对话的会话感知安全策略改进

Causal-aware Safe Policy Improvement for Task-oriented dialogue

Salesforce Research(赛富时研究院)

Govardana Sachithanandam Ramachandran, Kazuma Hashimoto, Caiming Xiong

摘要:

最近强化学习(RL)在解决复杂任务方面的成功通常归功于其探索和利用训练环境的能力。样本效率通常不是问题,因为便宜的模拟器可用于对策略上的数据进行采样。另一方面,面向任务的对话通常是从使用人类演示收集的离线数据中学习的。收集不同的演示并注释它们是昂贵的。不幸的是,使用在非政策数据上训练的RL方法容易出现偏差和泛化问题,这进一步加剧了人类响应的随机性和对话管理系统的非马尔可夫信念状态。为此,我们提出了一个面向任务的对话策略学习的批量强化学习框架:因果感知安全策略改进(CASPI)。这种方法保证了对话策略的性能,并根据人类响应背后的意图来学习塑造奖励,而不仅仅是模仿演示数据;这种与批量RL的结合有助于整体提高框架的样本效率。我们证明了这个框架的有效性对话上下文到文本生成和端到端的对话任务的Multiwoz2.0数据集。在这两种情况下,所提出的方法在这些指标上优于现有技术。在端到端的情况下,我们的方法只训练了10%的数据,在四个评估指标中有三个能够超过当前状态。

英文摘要:

The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap simulators are available to sample data on-policy. On the other hand, task oriented dialogues are usually learnt from offline data collected using human demonstrations. Collecting diverse demonstrations and annotating them is expensive. Unfortunately, use of RL methods trained on off-policy data are prone to issues of bias and generalization, which are further exacerbated by stochasticity in human response and non-markovian belief state of a dialogue management system. To this end, we propose a batch RL framework for task oriented dialogue policy learning: causal aware safe policy improvement (CASPI). This method gives guarantees on dialogue policy's performance and also learns to shape rewards according to intentions behind human responses, rather than just mimicking demonstration data; this couple with batch-RL helps overall with sample efficiency of the framework. We demonstrate the effectiveness of this framework on a dialogue-context-to-text Generation and end-to-end dialogue task of the Multiwoz2.0 dataset. The proposed method outperforms the current state of the art on these metrics, in both case. In the end-to-end case, our method trained only on 10\% of the data was able to out perform current state in three out of four evaluation metrics.

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。

↑