基于数据驱动的强化学习的虚拟角色动画控制
Data-Driven Reinforcement Learning for Virtual Character Animation Control
摘要：
虚拟角色动画控制是一个很有前途的研究课题，强化学习（RL）是一种有效的方法。虽然目前的工作已经有效地应用RL来描绘基于物理的技能，但由于缺乏与世界的物理交互，社会行为在设计奖励功能方面具有挑战性。另一方面，这些技能的数据驱动实现仅限于监督学习方法，这些方法需要大量的训练数据，并对泛化能力进行限制。在本文中，我们提出了RLAnimate，这是一种新的数据驱动的深度RL方法来解决这一挑战，我们将RL的优势与创建代理时从运动数据集学习的能力结合在一起。我们通过细化元素（如代理，环境，状态和动作）的概念角色，以利用角色动画域和基于模型的RL的属性的方式，形式化了用于训练代理的数学结构。使用我们的方法训练的代理学习通用的动画动态来描绘多种行为，使用迭代的RL训练过程，通过从运动捕捉剪辑中学习的表示来了解有效的行为。我们证明，通过训练描绘现实的指向和挥动行为的代理，我们的方法需要显着降低训练时间，并且相对于最先进的基于物理的RL方法，在训练过程中生成的样本集要少得多。此外，与现有的基于监督学习的动画代理相比，RLAimate需要有限的运动剪辑数据集来生成训练期间有效行为的表示。
英文摘要：
Virtual character animation control is a problem for which Reinforcement Learning (RL) is a viable approach. While current work have applied RL effectively to portray physics-based skills, social behaviours are challenging to design reward functions for, due to their lack of physical interaction with the world. On the other hand, data-driven implementations for these skills have been limited to supervised learning methods which require extensive training data and carry constraints on generalisability. In this paper, we propose RLAnimate, a novel data-driven deep RL approach to address this challenge, where we combine the strengths of RL together with an ability to learn from a motion dataset when creating agents. We formalise a mathematical structure for training agents by refining the conceptual roles of elements such as agents, environments, states and actions, in a way that leverages attributes of the character animation domain and model-based RL. An agent trained using our approach learns versatile animation dynamics to portray multiple behaviours, using an iterative RL training process, which becomes aware of valid behaviours via representations learnt from motion capture clips. We demonstrate, by training agents that portray realistic pointing and waving behaviours, that our approach requires a significantly lower training time, and substantially fewer sample episodes to be generated during training relative to state-of-the-art physics-based RL methods. Also, compared to existing supervised learning-based animation agents, RLAnimate needs a limited dataset of motion clips to generate representations of valid behaviours during training.
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。
