Imitation Learning with Recurrent Neural Networks
This work addresses the challenge of compounding errors in sequential prediction for machine learning practitioners, but it appears incremental as it builds on existing frameworks.
The paper tackles the problem of sequential prediction by unifying learning to search and recurrent neural networks, resulting in a more advanced imitation learning framework that enhances search space and training robustness.
We present a novel view that unifies two frameworks that aim to solve sequential prediction problems: learning to search (L2S) and recurrent neural networks (RNN). We point out equivalences between elements of the two frameworks. By complementing what is missing from one framework comparing to the other, we introduce a more advanced imitation learning framework that, on one hand, augments L2S s notion of search space and, on the other hand, enhances RNNs training procedure to be more robust to compounding errors arising from training on highly correlated examples.