Global Autoregressive Models (GAMs) are a recent proposal [Parshakova et al., CoNLL 2019] for exploiting global properties of sequences for data-efficient learning of seq2seq models. In the first phase of training, an Energy-Based model (EBM) over sequences is derived. This EBM has high representational power, but is unnormalized and cannot be directly exploited for sampling. To address this issue [Parshakova et al., CoNLL 2019] proposes a distillation technique, which can only be applied under limited conditions. By relating this problem to Policy Gradient techniques in RL, but in a \emph{distributional} rather than \emph{optimization} perspective, we propose a general approach applicable to any sequential EBM. Its effectiveness is illustrated on GAM-based experiments.
@article{arxiv.1912.08517,
title = {Distributional Reinforcement Learning for Energy-Based Sequential Models},
author = {Tetiana Parshakova and Jean-Marc Andreoli and Marc Dymetman},
journal= {arXiv preprint arXiv:1912.08517},
year = {2019}
}
Comments
OptRL workshop (Optimization Foundations for Reinforcement Learning) at Neurips 2019