We present a framework that enables the discovery of diverse and natural-looking motion strategies for athletic skills such as the high jump. The strategies are realized as control policies for physics-based characters. Given a task objective and an initial character configuration, the combination of physics simulation and deep reinforcement learning (DRL) provides a suitable starting point for automatic control policy training. To facilitate the learning of realistic human motions, we propose a Pose Variational Autoencoder (P-VAE) to constrain the actions to a subspace of natural poses. In contrast to motion imitation methods, a rich variety of novel strategies can naturally emerge by exploring initial character states through a sample-efficient Bayesian diversity search (BDS) algorithm. A second stage of optimization that encourages novel policies can further enrich the unique strategies discovered. Our method allows for the discovery of diverse and novel strategies for athletic jumping motions such as high jumps and obstacle jumps with no motion examples and less reward engineering than prior work.

中文翻译：

---

发现多样化的运动跳跃策略

我们提出了一个框架，该框架使人们能够发现诸如跳高之类的运动技能的各种自然外观的运动策略。这些策略被实现为基于物理角色的控制策略。给定任务目标和初始角色配置，物理模拟与深度强化学习（DRL）的结合为自动控制策略培训提供了合适的起点。为了便于学习逼真的人体运动，我们提出了一种姿态变化自动编码器（P-VAE），用于将动作限制在自然姿势的子空间中。与运动模仿方法相反，通过使用高效采样的贝叶斯分集搜索（BDS）算法探索初始字符状态，自然会涌现出各种各样的新颖策略。鼓励采用新颖政策的优化的第二阶段可以进一步丰富发现的独特策略。我们的方法允许发现运动跳跃动作（例如跳高和障碍物跳跃）的多种新颖策略，并且没有动作示例，而且与以前的工作相比，奖励工程更少。