تقرير
Time Adaptive Reinforcement Learning
العنوان: | Time Adaptive Reinforcement Learning |
---|---|
المؤلفون: | Reinke, Chris |
سنة النشر: | 2020 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning, I.2.6 |
الوصف: | Reinforcement learning (RL) allows to solve complex tasks such as Go often with a stronger performance than humans. However, the learned behaviors are usually fixed to specific tasks and unable to adapt to different contexts. Here we consider the case of adapting RL agents to different time restrictions, such as finishing a task with a given time limit that might change from one task execution to the next. We define such problems as Time Adaptive Markov Decision Processes and introduce two model-free, value-based algorithms: the Independent Gamma-Ensemble and the n-Step Ensemble. In difference to classical approaches, they allow a zero-shot adaptation between different time restrictions. The proposed approaches represent general mechanisms to handle time adaptive tasks making them compatible with many existing RL methods, algorithms, and scenarios. Comment: ICLR 2020 Workshop: Beyond Tabula Rasa in Reinforcement Learning |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2004.08600 |
رقم الأكسشن: | edsarx.2004.08600 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!