OGBench：离线目标条件强化学习基准测试
OGBench: Benchmarking Offline Goal-Conditioned RL
AI总结：
针对离线目标条件强化学习缺乏标准基准的问题，提出包含8类环境、85个数据集及6种算法参考实现的OGBench，可评估算法拼接、长horizon推理等能力，揭示其优缺点以助力新算法研发。
摘要：
离线目标条件强化学习（GCRL）是强化学习（RL）中的一个重要问题，因为它提供了一种简单、无监督且与领域无关的方法，无需奖励即可从未标记数据中获取多样化行为和表示。尽管该设置很重要，但我们缺乏一个能系统评估离线GCRL算法能力的标准基准。在这项工作中，我们提出OGBench，一个面向离线目标条件RL算法研究的新型高质量基准。OGBench包含8类环境、85个数据集以及6种代表性离线GCRL算法的参考实现。我们设计了这些具有挑战性且真实的环境和数据集，以直接探究算法的不同能力，如拼接、长 horizon 推理以及处理高维输入和随机性的能力。虽然代表性算法在先前基准上的排名相似，但我们的实验揭示了它们在这些不同能力上的显著优缺点，为构建新算法提供了坚实基础。项目页面：https://seohong.me/projects/ogbench
英文摘要：
Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled data without rewards. Despite the importance of this setting, we lack a standard benchmark that can systematically evaluate the capabilities of offline GCRL algorithms. In this work, we propose OGBench, a new, high-quality benchmark for algorithms research in offline goal-conditioned RL. OGBench consists of 8 types of environments, 85 datasets, and reference implementations of 6 representative offline GCRL algorithms. We have designed these challenging and realistic environments and datasets to directly probe different capabilities of algorithms, such as stitching, long-horizon reasoning, and the ability to handle high-dimensional inputs and stochasticity. While representative algorithms may rank similarly on prior benchmarks, our experiments reveal stark strengths and weaknesses in these different capabilities, providing a strong foundation for building new algorithms. Project page: https://seohong.me/projects/ogbench
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。
