Prioritized Experience Replay (PER) enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. However, this non-uniform sampling method shifts the state-action distribution that is originally used to estimate Q-value functions, which brings about the estimation deviation. In this article, an novel off policy reinforcement learning training framework called Directly Attention Loss Adjusted Prioritized Experience Replay (DALAP) is proposed, which can directly quantify the changed extent of the shifted distribution through Parallel Self-Attention network, so as to accurately compensate the error. In addition, a Priority-Encouragement mechanism is designed simultaneously to optimize the sample screening criterion, and further improve the training efficiency. In order to verify the effectiveness and generality of DALAP, we integrate it with the value-function based, the policy-gradient based and multi-agent reinforcement learning algorithm, respectively. The multiple groups of comparative experiments show that DALAP has the significant advantages of both improving the convergence rate and reducing the training variance.

翻译：优先经验回放（PER）通过人为改变样本的访问频率，使模型能够更多地学习相对重要的样本。然而，这种非均匀采样方法改变了原本用于估计Q值函数的状态-动作分布，从而引入了估计偏差。本文提出了一种新颖的离策略强化学习训练框架——直接注意力损失调整的优先经验回放（DALAP），该框架通过并行自注意力网络直接量化偏移分布的变化程度，从而精确补偿误差。此外，同时设计了一种优先级激励机制，以优化样本筛选标准，并进一步提高训练效率。为验证DALAP的有效性和通用性，我们分别将其与基于值函数、基于策略梯度以及多智能体强化学习算法相结合。多组对比实验表明，DALAP在提升收敛速度和降低训练方差方面均具有显著优势。