arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2303.02569cs.LG
收藏

基于松弛分布匹配的次优演示离线模仿学习

Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching

Stanford University(斯坦福大学);NVIDIA(英伟达)

Lantao Yu, Tianhe Yu, Jiaming Song, Willie Neiswanger, Stefano Ermon

摘要:

离线模仿学习(IL)承诺能够从预先收集的演示中学习性能策略,而无需与环境交互。然而,完全离线模仿行为通常需要大量的专家数据。为了解决这个问题,我们研究的设置,我们有有限的专家数据和补充次优数据。在这种情况下,一个众所周知的问题是学习策略和收集离线数据的行为策略之间的分布偏移。先前的工作通过正则化学习策略和行为策略的静态状态-动作分布之间的KL分歧来缓解这个问题。我们认为,这种基于精确分布匹配的约束可能过于保守,并妨碍策略学习,特别是当不完美的离线数据是高度次优的。为了解决这个问题,我们提出了RelaxDICE,它采用了非对称放松的f-发散显式支持正则化。具体来说,不是驱动学习的策略与行为策略完全匹配,而是只要它们的静态状态-动作分布之间的密度比由一个常数上界,我们就施加很少的惩罚。注意,这样的公式化导致嵌套的最小-最大优化问题,这在实践中导致不稳定性。RelaxDICE通过支持内部最大化问题的封闭形式解决方案来解决这一挑战。广泛的实证研究表明,我们的方法显着优于最好的先验离线IL方法在六个标准的连续控制环境中,平均超过30%的性能增益,在22个设置中,不完美的数据集是高度次优的。

英文摘要:

Offline imitation learning (IL) promises the ability to learn performant policies from pre-collected demonstrations without interactions with the environment. However, imitating behaviors fully offline typically requires numerous expert data. To tackle this issue, we study the setting where we have limited expert data and supplementary suboptimal data. In this case, a well-known issue is the distribution shift between the learned policy and the behavior policy that collects the offline data. Prior works mitigate this issue by regularizing the KL divergence between the stationary state-action distributions of the learned policy and the behavior policy. We argue that such constraints based on exact distribution matching can be overly conservative and hamper policy learning, especially when the imperfect offline data is highly suboptimal. To resolve this issue, we present RelaxDICE, which employs an asymmetrically-relaxed f-divergence for explicit support regularization. Specifically, instead of driving the learned policy to exactly match the behavior policy, we impose little penalty whenever the density ratio between their stationary state-action distributions is upper bounded by a constant. Note that such formulation leads to a nested min-max optimization problem, which causes instability in practice. RelaxDICE addresses this challenge by supporting a closed-form solution for the inner maximization problem. Extensive empirical study shows that our method significantly outperforms the best prior offline IL method in six standard continuous control environments with over 30% performance gain on average, across 22 settings where the imperfect dataset is highly suboptimal.

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。

↑