论文标题
基于图神经网络和自回归政策分解的象征性关系深度强化学习
Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition
论文作者
论文摘要
我们专注于在关系问题上自然定义的关系问题，其关系和以对象为中心的行动而定义的关系问题。这些问题的特征是可变状态和动作空间，并且很难（即使不是不可能）找到大多数现有RL方法所要求的固定长度表示。我们提出了一个基于图神经网络和自动回归政策分解的深度RL框架，该框架自然可以解决这些问题，并且完全不依赖于领域。我们证明了该框架在三个不同的域中的广泛适用性，并在不同的问题大小上显示出令人印象深刻的零击概括。
We focus on reinforcement learning (RL) in relational problems that are naturally defined in terms of objects, their relations, and object-centric actions. These problems are characterized by variable state and action spaces, and finding a fixed-length representation, required by most existing RL methods, is difficult, if not impossible. We present a deep RL framework based on graph neural networks and auto-regressive policy decomposition that naturally works with these problems and is completely domain-independent. We demonstrate the framework's broad applicability in three distinct domains and show impressive zero-shot generalization over different problem sizes.
