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 2211.09937cs.AIcs.CLcs.LG
收藏

通过因果性自我对话的可解释性

Explainability Via Causal Self-Talk

DeepMind(深度思维)

Nicholas A. Roy, Junkyung Kim, Neil Rabinowitz

摘要:

解释人工智能系统的行为是一个重要的问题,在实践中,通常是避免的。虽然XAI社区已经开发了大量的技术,但大多数技术都会产生一系列成本,而更广泛的深度学习社区在大多数情况下都不愿意支付这些成本。我们对这个问题采取了务实的观点,并定义了一套既能抓住XAI的雄心,又能抓住深度学习的实际限制的必要条件。我们描述了一种有效的方法来满足所有的desiderata:训练人工智能系统建立自己的因果模型。我们为深度RL代理开发了一个解决方案的实例:因果自我对话。CST通过训练智能体跨时间与自身进行通信来运行。我们在一个模拟的3D环境中实现了这种方法,并展示了它如何使代理生成忠实的和语义上有意义的解释自己的行为。除了解释之外,我们还证明了这些学习模型提供了为AI系统构建语义控制接口的新方法。

英文摘要:

Explaining the behavior of AI systems is an important problem that, in practice, is generally avoided. While the XAI community has been developing an abundance of techniques, most incur a set of costs that the wider deep learning community has been unwilling to pay in most situations. We take a pragmatic view of the issue, and define a set of desiderata that capture both the ambitions of XAI and the practical constraints of deep learning. We describe an effective way to satisfy all the desiderata: train the AI system to build a causal model of itself. We develop an instance of this solution for Deep RL agents: Causal Self-Talk. CST operates by training the agent to communicate with itself across time. We implement this method in a simulated 3D environment, and show how it enables agents to generate faithful and semantically-meaningful explanations of their own behavior. Beyond explanations, we also demonstrate that these learned models provide new ways of building semantic control interfaces to AI systems.

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。

↑