论文标题
IGN：隐性生成网络
IGN : Implicit Generative Networks
论文作者
论文摘要
在这项工作中，我们建立了分配强化学习的最新进展，以基于IQN提供模型的最新分配变体。我们通过使用GAN模型的生成器和鉴别器功能与分位数回归来实现这一目标，从而近似于状态返回分布的完整分位数。我们在基线数据集中证明了性能提高-57 Atari 2600啤酒中的啤酒。此外，我们使用算法来显示Atari游戏中风险敏感政策的最新培训表现，并通过政策优化和评估。
In this work, we build recent advances in distributional reinforcement learning to give a state-of-art distributional variant of the model based on the IQN. We achieve this by using the GAN model's generator and discriminator function with the quantile regression to approximate the full quantile value for the state-action return distribution. We demonstrate improved performance on our baseline dataset - 57 Atari 2600 games in the ALE. Also, we use our algorithm to show the state-of-art training performance of risk-sensitive policies in Atari games with the policy optimization and evaluation.
