Antonio Pio Ricciardi

Antonio Pio Ricciardi, Valentino Maiorca, Luca Moschella et al.

Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. It is known that variations in input domains (e.g., different panorama colors due to seasonal changes) or task domains (e.g., altering the target speed of a car) can disrupt agent performance, necessitating new training for each variation. Recent advancements in the field of representation learning have demonstrated the possibility of combining components from different neural networks to create new models in a zero-shot fashion. In this paper, we build upon relative representations, a framework that maps encoder embeddings to a universal space. We adapt this framework to the Visual Reinforcement Learning setting, allowing to combine agents components to create new agents capable of effectively handling novel visual-task pairs not encountered during training. Our findings highlight the potential for model reuse, significantly reducing the need for retraining and, consequently, the time and computational resources required.

Antonio Pio Ricciardi, Valentino Maiorca, Luca Moschella et al.

Deep Reinforcement Learning (RL) models often fail to generalize when even small changes occur in the environment's observations or task requirements. Addressing these shifts typically requires costly retraining, limiting the reusability of learned policies. In this paper, we build on recent work in semantic alignment to propose a zero-shot method for mapping between latent spaces across different agents trained on different visual and task variations. Specifically, we learn a transformation that maps embeddings from one agent's encoder to another agent's encoder without further fine-tuning. Our approach relies on a small set of "anchor" observations that are semantically aligned, which we use to estimate an affine or orthogonal transform. Once the transformation is found, an existing controller trained for one domain can interpret embeddings from a different (existing) encoder in a zero-shot fashion, skipping additional trainings. We empirically demonstrate that our framework preserves high performance under visual and task domain shifts. We empirically demonstrate zero-shot stitching performance on the CarRacing environment with changing background and task. By allowing modular re-assembly of existing policies, it paves the way for more robust, compositional RL in dynamically changing environments.