arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.08466cs.LGcs.AIcs.RO
收藏

简化基于模型的强化学习:用单一目标学习表征、潜空间模型和策略

Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective

VNIT Nagpur(那格浦尔国家技术学院);Carnegie Mellon University(卡内基梅隆大学);UC Berkeley(加州大学伯克利分校)

Raj Ghugare, Homanga Bharadhwaj, Benjamin Eysenbach, Sergey Levine, Ruslan Salakhutdinov

AI总结:

提出单一目标联合优化潜空间模型与策略,直接作为预期回报下界,在匹配或提升样本效率的同时大幅减少计算时间。

摘要:

尽管学习环境内部模型的强化学习(RL)方法有望比无模型方法具有更高的样本效率,但学习对来自高维传感器的原始观测进行建模可能具有挑战性。先前的工作通过辅助目标(如重建或价值预测)学习观测的低维表征来解决这一挑战。然而,这些辅助目标与RL目标之间的对齐通常不明确。在这项工作中,我们提出了一个单一目标,联合优化潜空间模型和策略,以在保持自洽的同时实现高回报。该目标是预期回报的下界。与先前基于模型的RL关于策略探索或模型保证的界限不同,我们的界限直接作用于整体RL目标。我们证明,所得算法匹配或提升了最佳先前基于模型和无模型RL方法的样本效率。虽然样本高效的方法通常计算需求高,但我们的方法在约50%更少的实际运行时间内达到了SAC的性能。

英文摘要:

While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors can be challenging. Prior work has addressed this challenge by learning low-dimensional representation of observations through auxiliary objectives, such as reconstruction or value prediction. However, the alignment between these auxiliary objectives and the RL objective is often unclear. In this work, we propose a single objective which jointly optimizes a latent-space model and policy to achieve high returns while remaining self-consistent. This objective is a lower bound on expected returns. Unlike prior bounds for model-based RL on policy exploration or model guarantees, our bound is directly on the overall RL objective. We demonstrate that the resulting algorithm matches or improves the sample-efficiency of the best prior model-based and model-free RL methods. While sample efficient methods typically are computationally demanding, our method attains the performance of SAC in about 50% less wall-clock time.

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。

↑