跳到正文
原文
OpenAI News·· 2017-07-27AI 评分15

OpenAI 提出参数噪声增强强化学习探索

Better exploration with parameter noise

AI 导读

OpenAI 发现向强化学习算法参数添加自适应噪声能频繁提升性能。该方法实现简单且极少降低表现,适用于各类问题场景。

原文

We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method is simple to implement and very rarely decreases performance, so it’s worth trying on any problem.

来源:OpenAI News · openai.com