Adaptive Transformers in RL
This work addresses efficiency and performance in partially observable RL tasks, but it is incremental as it builds on prior Transformer stabilization methods.
The paper tackled improving Transformer performance in reinforcement learning by adding adaptive attention span, achieving better results with less computation on the DMLab30 environment.
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.