SQT --标准品$Q$ -目标
SQT -- std $Q$-target
摘要：
Std $Q$ -target是一种保守的、actor-critic的、集成的、基于$Q$学习的算法，它基于单个关键$Q$ -公式：$Q$ -网络标准差，这是一种“不确定性惩罚”，并且用作高估偏倚问题的最小化解决方案。我们在TD 3/TD 7代码上实现了SQT，并在七个流行的MuJoCo和Bullet任务上对最先进的（SOTA）演员-评论家算法DDPG，TD 3和TD 7进行了测试。我们的研究结果表明，SQT的$Q$ -目标公式优于TD 3的$Q$ -目标公式作为RL高估偏差的保守解决方案，而SQT在所有任务上都表现出明显的性能优势，优于DDPG，TD 3和TD 7。
英文摘要：
Std $Q$-target is a conservative, actor-critic, ensemble, $Q$-learning-based algorithm, which is based on a single key $Q$-formula: $Q$-networks standard deviation, which is an "uncertainty penalty", and, serves as a minimalistic solution to the problem of overestimation bias. We implement SQT on top of TD3/TD7 code and test it against the state-of-the-art (SOTA) actor-critic algorithms, DDPG, TD3 and TD7 on seven popular MuJoCo and Bullet tasks. Our results demonstrate SQT's $Q$-target formula superiority over TD3's $Q$-target formula as a conservative solution to overestimation bias in RL, while SQT shows a clear performance advantage on a wide margin over DDPG, TD3, and TD7 on all tasks.
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。
