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 2011.12363cs.LGcs.AIstat.ML
收藏

C-Learning:水平感知的累积可达性估计

C-Learning: Horizon-Aware Cumulative Accessibility Estimation

Layer 6 AI(Layer 6人工智能公司);University of Toronto(多伦多大学);Vector Institute(矢量研究所);Nvidia(英伟达)

Panteha Naderian, Gabriel Loaiza-Ganem, Harry J. Braviner, Anthony L. Caterini, Jesse C. Cresswell, Tong Li, Animesh Garg

摘要:

多目标到达问题是强化学习中实现算法泛化的一个重要问题。尽管最近在这一领域的进展,目前的算法遭受三个主要的挑战:高样本的复杂性,学习只有一种方式达到的目标,并在解决复杂的运动规划任务的困难。为了解决这些局限性,我们引入了累积可达性函数的概念,它可以衡量目标在指定范围内从给定状态的可达性。我们表明,这些功能服从递归关系,这使得学习离线交互。我们还证明了最佳的累积可达性函数是单调的规划视野。此外,我们的方法可以权衡速度和可靠性的目标达成建议多个路径到一个单一的目标取决于所提供的地平线。我们评估我们的方法上的一组多目标离散和连续控制任务。我们表明,我们的方法优于国家的最先进的目标达到算法的成功率,样本的复杂性和路径最优性。我们的代码可以在https://github.com/layer6ai-labs/CAE上找到,其他可视化可以在https://sites.google.com/view/learning-cae/上找到。

英文摘要:

Multi-goal reaching is an important problem in reinforcement learning needed to achieve algorithmic generalization. Despite recent advances in this field, current algorithms suffer from three major challenges: high sample complexity, learning only a single way of reaching the goals, and difficulties in solving complex motion planning tasks. In order to address these limitations, we introduce the concept of cumulative accessibility functions, which measure the reachability of a goal from a given state within a specified horizon. We show that these functions obey a recurrence relation, which enables learning from offline interactions. We also prove that optimal cumulative accessibility functions are monotonic in the planning horizon. Additionally, our method can trade off speed and reliability in goal-reaching by suggesting multiple paths to a single goal depending on the provided horizon. We evaluate our approach on a set of multi-goal discrete and continuous control tasks. We show that our method outperforms state-of-the-art goal-reaching algorithms in success rate, sample complexity, and path optimality. Our code is available at https://github.com/layer6ai-labs/CAE, and additional visualizations can be found at https://sites.google.com/view/learning-cae/.

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。

↑