yaserkl/RLSeq2Seq

Deep Reinforcement Learning For Sequence to Sequence Models

51
/ 100
Established

Implements policy-gradient with self-critic learning and actor-critic methods (DDQN, dueling networks) to address exposure bias and train/test measurement inconsistency in seq2seq models. Built on TensorFlow 1.10.1, it supports scheduled sampling variants and intra-decoder attention mechanisms, with pre-processed CNN/Daily Mail and Newsroom datasets for abstractive text summarization tasks.

768 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

768

Forks

161

Language

Python

License

MIT

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yaserkl/RLSeq2Seq"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.