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 2101.09207cs.LGcs.ITmath.IT
收藏

用于深度强化学习的可微信赖域层

Differentiable Trust Region Layers for Deep Reinforcement Learning

Bosch Center for Artificial Intelligence(博世人工智能中心);University of Tübingen(蒂宾根大学);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Fabian Otto, Philipp Becker, Ngo Anh Vien, Hanna Carolin Ziesche, Gerhard Neumann

摘要:

信赖域方法是强化学习中的一种流行工具,因为它们在连续和离散动作空间中产生鲁棒的策略更新。然而,在深度强化学习中实施这样的信任区域是困难的。因此,诸如信任域策略优化(TRPO)和近端策略优化(PPO)的许多方法是基于近似的。由于这些近似,它们违反了约束条件或无法在信赖域内找到最优解。此外,它们很难实施,往往缺乏足够的探索,并已被证明依赖于看似无关的实施选择。在这项工作中,我们提出了可微神经网络层,通过封闭形式的投影来执行深度高斯策略的信任区域。与现有的方法不同,这些层分别为每个状态形式化信任区域,并可以补充现有的强化学习算法。我们推导出基于Kullback-Leibler散度,Wasserstein L2距离和高斯分布的Frobenius范数的信赖域预测。我们的经验表明,这些投影层实现类似或更好的结果比现有的方法,同时几乎不可知的具体实施选择。该代码可在https://git.io/Jthb0上获得。

英文摘要:

Trust region methods are a popular tool in reinforcement learning as they yield robust policy updates in continuous and discrete action spaces. However, enforcing such trust regions in deep reinforcement learning is difficult. Hence, many approaches, such as Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), are based on approximations. Due to those approximations, they violate the constraints or fail to find the optimal solution within the trust region. Moreover, they are difficult to implement, often lack sufficient exploration, and have been shown to depend on seemingly unrelated implementation choices. In this work, we propose differentiable neural network layers to enforce trust regions for deep Gaussian policies via closed-form projections. Unlike existing methods, those layers formalize trust regions for each state individually and can complement existing reinforcement learning algorithms. We derive trust region projections based on the Kullback-Leibler divergence, the Wasserstein L2 distance, and the Frobenius norm for Gaussian distributions. We empirically demonstrate that those projection layers achieve similar or better results than existing methods while being almost agnostic to specific implementation choices. The code is available at https://git.io/Jthb0.

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。

↑