Offline reinforcement learning algorithms have proven effective on datasets highly connected to the target downstream task. Yet, leveraging a novel testbed (MOOD) in which trajectories come from heterogeneous sources, we show that existing methods struggle with diverse data: their performance considerably deteriorates as data collected for related but different tasks is simply added to the offline buffer. In light of this finding, we conduct a large empirical study where we formulate and test several hypotheses to explain this failure. Surprisingly, we find that scale, more than algorithmic considerations, is the key factor influencing performance. We show that simple methods like AWAC and IQL with increased network size overcome the paradoxical failure modes from the inclusion of additional data in MOOD, and notably outperform prior state-of-the-art algorithms on the canonical D4RL benchmark.

离线强化学习算法被证明在与目标下游任务高度相关的数据集上非常有效，然而，在轨迹来自不同源头的新测试平台（MOOD）上，我们发现现有方法在面对不同数据时效果明显下降：随着收集到的与任务相关但不同的数据简单地添加到离线缓冲区，它们的性能显著恶化。鉴于此发现，我们进行了大规模经验证明，规模是影响性能的关键因素而非算法上的考虑。我们展示了简单的方法（如AWAC和IQL）通过增加网络规模来克服MOOD中添加附加数据所产生的悖论性失败，且在经典的D4RL基准测试中明显优于先前的最新算法。

离线强化学习的简单成分