In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications
This addresses the challenge of generalization in reinforcement learning for formally specified tasks, but it appears incremental as it builds on existing neuro-symbolic frameworks.
The paper tackles the problem of building agents that learn to execute out-of-distribution multi-task instructions expressed in temporal logic using deep reinforcement learning, proposing a new deep learning configuration with inductive biases that generate latent goal representations to improve generalization performance.
We address the problem of building agents whose goal is to learn to execute out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinforcement learning (DRL). Recent works provided evidence that the agent's neural architecture is a key feature when DRL agents are learning to solve OOD tasks in TL. Yet, the studies on this topic are still in their infancy. In this work, we propose a new deep learning configuration with inductive biases that lead agents to generate latent representations of their current goal, yielding a stronger generalization performance. We use these latent-goal networks within a neuro-symbolic framework that executes multi-task formally-defined instructions and contrast the performance of the proposed neural networks against employing different state-of-the-art (SOTA) architectures when generalizing to unseen instructions in OOD environments.