AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation

Chun-Hsing Lin, Siang-Ruei Wu, Hung-yi Lee, Yun-Nung Chen

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Alternative policy update rules · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Taylor neighbor augmentation instead of the Gumbel-Softmax estimatorTaylorGAN on EMNLP 2017 News validation · EMNLP 2017 News valFED: 0.0218 -> 0.0149Improved
Use Taylor neighbor augmentation instead of the REINFORCE estimatorTaylorGAN on EMNLP 2017 News validation · EMNLP 2017 News valFED: 0.0181 -> 0.0149Improved
Use Taylor neighbor augmentation instead of the Straight-Through estimatorTaylorGAN on EMNLP 2017 News validation · EMNLP 2017 News valFED: 0.0449 -> 0.0149Improved
Increase bandwidth Λ from 0.50 to 1.00 (ablation)TaylorGAN · EMNLP 2017 News valPerplexity: 72 -> 60Improved
Increase bandwidth Λ from 0.50 to 1.00 (ablation)TaylorGAN · EMNLP 2017 News valFED: 0.0149 -> 0.0199Hurt
Increase discriminator constraint λSN from 0.07 to 0.10 (ablation)TaylorGAN · EMNLP 2017 News valPerplexity: 72 -> 64Improved
Increase discriminator constraint λSN from 0.07 to 0.10 (ablation)TaylorGAN · EMNLP 2017 News valFED: 0.0149 -> 0.0178Hurt
Reduce discriminator constraint λSN from 0.07 to 0.01 (ablation)TaylorGAN · EMNLP 2017 News valPerplexity: 72 -> 99Hurt
Remove entropy maximization (ablation)TaylorGAN · EMNLP 2017 News valPerplexity: 72 -> 310Hurt
Increase bandwidth Λ from 0.50 to 0.25 (ablation)TaylorGAN · EMNLP 2017 News valFED: 0.0149 -> 0.0179Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy