论文标题
风格的敏捷增强学习
Style-Agnostic Reinforcement Learning
论文作者
论文摘要
我们提出了一种新颖的方法，即在强化学习框架中使用样式转移和对抗性学习的样式转移和对抗性学习。在这里，样式是指任务 - 涉及到的细节，例如图像中背景的颜色，在这种情况下，在具有不同样式的环境中概括学到的策略仍然是一个挑战。我们的方法着眼于学习样式不可思议的表示，以固有的对抗性风格的扰动生成器产生的各种图像样式训练演员，该样式在演员和发电机之间扮演最小游戏，而无需对数据增强的专家知识或对对抗性培训进行其他类别的专家知识。我们验证我们的方法比Procgen的最先进方法和分散控制套件的基准的最先进方法能够实现竞争性或更好的性能，并进一步研究了从我们的模型中提取的功能，表明该模型可以更好地捕获不变性，并且不太因转移风格而分心。该代码可在https://github.com/postech-cvlab/style-agnostic-rl上找到。
We present a novel method of learning style-agnostic representation using both style transfer and adversarial learning in the reinforcement learning framework. The style, here, refers to task-irrelevant details such as the color of the background in the images, where generalizing the learned policy across environments with different styles is still a challenge. Focusing on learning style-agnostic representations, our method trains the actor with diverse image styles generated from an inherent adversarial style perturbation generator, which plays a min-max game between the actor and the generator, without demanding expert knowledge for data augmentation or additional class labels for adversarial training. We verify that our method achieves competitive or better performances than the state-of-the-art approaches on Procgen and Distracting Control Suite benchmarks, and further investigate the features extracted from our model, showing that the model better captures the invariants and is less distracted by the shifted style. The code is available at https://github.com/POSTECH-CVLab/style-agnostic-RL.
