Adaptive Transformers in RL

April 08, 2020 · Entered Twilight · 🏛 arXiv.org

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, Implementations, Model, README.md, StableTransformersReplication, Transformer-XLCode, adaptive_span2, dqn.py, old_monobeast_test.py, old_transformer_xl.py, replayBuffer.py, requirements.txt, tester.py, torchbeast, train.py, transformerDqn.py

Authors Shakti Kumar, Jerrod Parker, Panteha Naderian arXiv ID 2004.03761 Category cs.LG: Machine Learning Cross-listed cs.AI, cs.NE Citations 17 Venue arXiv.org Repository https://github.com/jerrodparker20/adaptive-transformers-in-rl ⭐ 136 Last Checked 4 months ago

Abstract

Recent developments in Transformers have opened new interesting areas of research in partially observable reinforcement learning tasks. Results from late 2019 showed that Transformers are able to outperform LSTMs on both memory intense and reactive tasks. In this work we first partially replicate the results shown in Stabilizing Transformers in RL on both reactive and memory based environments. We then show performance improvement coupled with reduced computation when adding adaptive attention span to this Stable Transformer on a challenging DMLab30 environment. The code for all our experiments and models is available at https://github.com/jerrodparker20/adaptive-transformers-in-rl.