Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstractions to generalize better in novel situations. It automatically decomposes the given task into smaller, more manageable subtasks, and thus enables sparse decision-making and focused computation on the relevant parts of the environment. The decomposition relies on the extraction of an abstracted proxy problem represented as a directed graph, in which vertices and edges are learned end-to-end from hindsight. Our theoretical analyses provide performance guarantees under appropriate assumptions and establish where our approach is expected to be helpful. Generalization-focused experiments validate Skipper's significant advantage in zero-shot generalization, compared to some existing state-of-the-art hierarchical planning methods.
@article{arxiv.2310.00229,
title = {Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning},
author = {Mingde Zhao and Safa Alver and Harm van Seijen and Romain Laroche and Doina Precup and Yoshua Bengio},
journal= {arXiv preprint arXiv:2310.00229},
year = {2024}
}