Over the last few years, we have not seen any major developments in model-free or model-based learning methods that would make one obsolete relative to the other. In most cases, the used technique is heavily dependent on the use case scenario or other attributes, e.g. the environment. Both approaches have their own advantages, for example, sample efficiency or computational efficiency. However, when combining the two, the advantages of each can be combined and hence achieve better performance. The TD-MPC framework is an example of this approach. On the one hand, a world model in combination with model predictive control is used to get a good initial estimate of the value function. On the other hand, a Q function is used to provide a good long-term estimate. Similar to algorithms like MuZero a latent state representation is used, where only task-relevant information is encoded to reduce the complexity. In this paper, we propose the use of a reconstruction function within the TD-MPC framework, so that the agent can reconstruct the original observation given the internal state representation. This allows our agent to have a more stable learning signal during training and also improves sample efficiency. Our proposed addition of another loss term leads to improved performance on both state- and image-based tasks from the DeepMind-Control suite.

翻译：近年来，无模型与基于模型的学习方法并未出现重大突破，以致于哪种方法取代另一种。在大多数情况下，采用的技术高度依赖于使用场景或其他属性，例如环境。两种方法各有优势，如样本效率或计算效率。然而，将两者结合时，可以整合各自的优势，从而获得更好的性能。TD-MPC框架便是这一方法的实例。一方面，结合世界模型与模型预测控制来获取价值函数的良好初始估计；另一方面，使用Q函数提供准确的长期估计。与MuZero等算法类似，该框架采用潜在状态表示，仅编码与任务相关的信息以降低复杂性。本文提出在TD-MPC框架中引入重构函数，使智能体能够根据内部状态表示重构原始观测值。这不仅为训练过程提供了更稳定的学习信号，还提升了样本效率。我们提出的附加损失项在DeepMind-Control套件的状态与图像任务中均实现了性能改进。