arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1710.04423cs.LG
收藏

AMBER:用于连续动作控制的自适应多批次经验回放

AMBER: Adaptive Multi-Batch Experience Replay for Continuous Action Control

KAIST(韩国科学技术院)

Seungyul Han, Youngchul Sung

摘要:

针对连续动作控制中的近端策略优化问题,提出了一种新的自适应多批次经验重放方案。与原有的PPO算法不同,该算法使用过去策略的批量样本和当前策略进行下一个策略的更新,其中所使用的过去批次的数量是根据平均重要性采样(IS)权重衡量的过去批次的陈旧性自适应确定的.新算法将PPO与多批次经验回放方案相结合,通过存储预先计算的优点和值以及自适应地确定小批次大小,保持了原始PPO的优点,如随机小批次采样和低IS权重导致的小偏差。数值结果表明,所提出的方法显着提高了收敛速度和稳定性的各种连续控制任务相比,原来的PPO。

英文摘要:

In this paper, a new adaptive multi-batch experience replay scheme is proposed for proximal policy optimization (PPO) for continuous action control. On the contrary to original PPO, the proposed scheme uses the batch samples of past policies as well as the current policy for the update for the next policy, where the number of the used past batches is adaptively determined based on the oldness of the past batches measured by the average importance sampling (IS) weight. The new algorithm constructed by combining PPO with the proposed multi-batch experience replay scheme maintains the advantages of original PPO such as random mini-batch sampling and small bias due to low IS weights by storing the pre-computed advantages and values and adaptively determining the mini-batch size. Numerical results show that the proposed method significantly increases the speed and stability of convergence on various continuous control tasks compared to original PPO.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑