Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected, static datasets without further interaction. However, in practice, offline RL presents a major challenge, and standard off-policy RL methods can fail due to overestimation of values induced by the distributional shift between the dataset and the learned policy, especially when training on complex and multi-modal data distributions. In this paper, we propose conservative Q-learning (CQL), which aims to address these limitations by learning a conservative Q-function such that the expected value of a policy under this Q-function lower-bounds its true value. We theoretically show that CQL produces a lower bound on the value of the current policy and that it can be incorporated into a principled policy improvement procedure. In practice, CQL augments the standard Bellman error objective with a simple Q-value regularizer which is straightforward to implement on top of existing deep Q-learning and actor-critic implementations. On both discrete and continuous control domains, we show that CQL substantially outperforms existing offline RL methods, often learning policies that attain 2-5 times higher final return, especially when learning from complex and multi-modal data distributions.

本论文提出了保守型 Q-learning（CQL），通过学习保守型 Q 函数以得到预期值，有效地解决了离线强化学习（offline RL）中的价值估计问题，从而提高了学习性能。在实验中，我们将 CQL 应用于复杂和多模态数据分布，证明其在离线 RL 方法中的优越性，能学习到比现有离线 RL 方法 2 到 5 倍更高的最终回报的策略

离线强化学习的保守型 Q 学习