تقرير
Parameter Space Noise for Exploration
العنوان: | Parameter Space Noise for Exploration |
---|---|
المؤلفون: | Plappert, Matthias, Houthooft, Rein, Dhariwal, Prafulla, Sidor, Szymon, Chen, Richard Y., Chen, Xi, Asfour, Tamim, Abbeel, Pieter, Andrychowicz, Marcin |
سنة النشر: | 2017 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary Computing, Computer Science - Robotics, Statistics - Machine Learning |
الوصف: | Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use parameter perturbations, but discard all temporal structure in the process and require significantly more samples. Combining parameter noise with traditional RL methods allows to combine the best of both worlds. We demonstrate that both off- and on-policy methods benefit from this approach through experimental comparison of DQN, DDPG, and TRPO on high-dimensional discrete action environments as well as continuous control tasks. Our results show that RL with parameter noise learns more efficiently than traditional RL with action space noise and evolutionary strategies individually. Comment: Updated to camera-ready ICLR submission |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/1706.01905 |
رقم الأكسشن: | edsarx.1706.01905 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |