Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar environments. Data augmentation has recently been shown to improve the sample efficiency and generalization of RL agents. However, different tasks tend to benefit from different kinds of data augmentation. In this paper, we compare three approaches for automatically finding an appropriate augmentation. These are combined with two novel regularization terms for the policy and value function, required to make the use of data augmentation theoretically sound for certain actor-critic algorithms. We evaluate our methods on the Procgen benchmark which consists of 16 procedurally-generated environments and show that it improves test performance by ~40% relative to standard RL algorithms. Our agent outperforms other baselines specifically designed to improve generalization in RL. In addition, we show that our agent learns policies and representations that are more robust to changes in the environment that do not affect the agent, such as the background. Our implementation is available at https://github.com/rraileanu/auto-drac.

本文通过比较三种方法，探究如何寻找适当的数据增强方式，并结合两个新的正则化项，以理论上的方式为某些 actor-critic 算法的数据增广提供支持，最终在 Procgen 基准测试上展示了在相对于标准 RL 算法提高了 ~40% 的测试性能。我们的代理优于其他针对 RL 中泛化改进的基线。此外，我们还展示了我们的代理学习出更能适应环境变化的策略和表示，包括不保留背景信息的变化。

深度强化学习中的自动数据增强以实现泛化能力