DICOMP: Deep Reinforcement Learning for Integer Compression

This paper presents DICOMP (Deep Reinforcement Learning for Integer Compression), a novel approach that employs Deep Reinforcement Learning (DRL) to optimize integer compression. DICOMP is the first known approach to apply reinforcement learning specifically to integer compression, filling a significant gap in current research. Unlike traditional methods based on statistical or dictionary techniques, DICOMP formulates compression as a sequential decision-making problem. The core innovation involves a DRL agent that explores various mathematical operations to minimize an integer’s memory size. The discovered optimal strategy was dividing by a set of four prime factors, which effectively transforms its representation into a compact base-4 encoding. This process enables lossless size reduction without relying on hand-crafted strategies. Experiments on diverse datasets show that this invented strategy achieves a reduction in size of more than 80%, outperforming both traditional and other learning-based methods. Despite its learning-based nature, it maintains competitive speed and decompression efficiency, making it practical for use in resource-constrained environments. DICOMP thus represents a significant advancement in intelligent, efficient, and flexible compression techniques. • Introduced DICOMP, the first DRL-based framework for lossless integer compression. • DICOMP discovered prime-factor division as an optimal compression strategy. • DICOMP avoids the usage of external metadata or descriptors for better compression. • Benchmarks show DICOMP outperforms RL and traditional compression methods. • DICOMP ensures low memory use and fast decompression for resource-constrained systems.