论文标题
RL中的自适应变压器
Adaptive Transformers in RL
论文作者
论文摘要
变形金刚的最新发展已在部分可观察到的强化学习任务中开辟了新的有趣的研究领域。 2019年底的结果表明，变形金刚能够在内存强度和反应性任务上均超过LSTM。在这项工作中，我们首先部分复制了在反应性和基于内存的环境上稳定RL中的变压器所显示的结果。然后，我们显示出性能改善，并在充满挑战的DMLAB30环境中向该稳定的变压器添加自适应注意跨度时的计算减少。我们所有实验和模型的代码均可在https://github.com/jerrodparker20/adaptive-transformers-in-rl上获得。
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.
