论文标题
重新理解经常性策略网络的有限状态表示
Re-understanding Finite-State Representations of Recurrent Policy Networks
论文作者
论文摘要
我们介绍了一种理解以复发性神经网络为代表的控制政策的方法。最近的工作通过将这种经常性的策略网络转换为有限状态机器（FSM），然后分析等效最小化的FSM，从而解决了这一问题。尽管这导致了有趣的见解，但最小化过程可以通过合并语义上不同的状态来更深入地了解机器的操作。为了解决这个问题，我们介绍了一种分析方法，该方法以未限制的FSM开头，并应用更清晰的减少，以保留政策的关键决策点。我们还为注意力工具提供了贡献，以更深入地了解观察在决策中的作用。我们对7场Atari游戏和3个控制基准测试的案例研究表明，该方法可以揭示以前没有注意到的见解。
We introduce an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this problem by transforming such recurrent policy networks into finite-state machines (FSM) and then analyzing the equivalent minimized FSM. While this led to interesting insights, the minimization process can obscure a deeper understanding of a machine's operation by merging states that are semantically distinct. To address this issue, we introduce an analysis approach that starts with an unminimized FSM and applies more-interpretable reductions that preserve the key decision points of the policy. We also contribute an attention tool to attain a deeper understanding of the role of observations in the decisions. Our case studies on 7 Atari games and 3 control benchmarks demonstrate that the approach can reveal insights that have not been previously noticed.
