PRISE: Learning Temporal Action Abstractions as a Sequence Compression Problem

arXiv:2402.10450v1 Announce Type: new
Abstract: Temporal action abstractions, along with belief state representations, are a powerful knowledge sharing mechanism for sequential decision making. In this work, we propose a novel view that treats inducing temporal action abstractions as a sequence compression problem. To do so, we bring a subtle but critical component of LLM training pipelines -- input tokenization via byte pair encoding (BPE) -- to the seemingly distant task of learning skills of variable time span in continuous control …

abstractions arxiv compression cs.lg temporal type