“Here is a link to the underlying study, for people who are interested in digging into the data themselves: http://arxiv.org/pdf/1509.06461v1.pdf”
Deep Reinforcement Learning with Double Q-learning
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively. In particular, we first show that the recent DQN algorithm, which combines Q-learning with a deep neural network, suffers from substantial overestimations in some games in the Atari 2600 domain. We then show that the idea behind the Double Q-learning algorithm, which was introduced in a tabular setting, can be generalized to work with large-scale function approximation. We propose a specific adaptation to the DQN algorithm and show that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“I think the article's analysis of overapproximation bias is correct. The issue is that due to the Max operator in the Q learning noise is amplified over timesteps. Some methods to reduce this bias, such as https://arxiv.org/abs/1509.06461 were successful in improving the RL agents performance. Studies have found that this happens even more for the states …”
- DeepMind: Deep Reinforcement Learning with Double Q Learning ↗vonnik · 2015-09-23 · 3 分