# Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning

arXiv: https://arxiv.org/abs/2602.12146 · HTML: https://mlsanity.com/paper/2602.12146/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [Reinforcement Learning with Prototypical Representations](https://mlsanity.com/paper/2102.11271/) (2021)
- [Transformer Language Models without Positional Encodings Still Learn Positional Information](https://mlsanity.com/paper/2203.16634/) (2022)
- [Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks](https://mlsanity.com/paper/2102.02017/) (2021)
- [DeepZip: Lossless Data Compression using Recurrent Neural Networks](https://mlsanity.com/paper/1811.08162/) (2018)
- [DECORE: Deep Compression with Reinforcement Learning](https://mlsanity.com/paper/2106.06091/) (2021)
- [TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning](https://mlsanity.com/paper/2409.13035/) (2024)
- [Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data](https://mlsanity.com/paper/2410.05078/) (2024)
- [Generalized Rational Variable Projection With Application in ECG Compression](https://mlsanity.com/paper/2003.00058/) (2020)
- [An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios](https://mlsanity.com/paper/2102.03138/) (2021)
- [Recursive Least Squares Advantage Actor-Critic Algorithms](https://mlsanity.com/paper/2201.05918/) (2022)

## Abstract (arXiv)

Efficient lossless compression is essential for minimizing storage costs and transmission overhead while preserving data integrity. Traditional compression techniques, such as dictionary-based and statistical methods, often struggle to optimally exploit the structure and redundancy in complex data formats. Recent advancements in deep learning have opened new avenues for compression; however, many existing approaches depend on dense vector representations that obscure the underlying token structure. To address these limitations, we propose a novel lossless compression method that leverages Reinforcement Learning applied to a T5 language model architecture. This approach enables the compression of data into sequences of tokens rather than traditional vector representations. Unlike auto-encoders, which typically encode information into continuous latent spaces, our method preserves the token-based structure, aligning more closely with the original data format. This preservation allows for higher compression ratios while maintaining semantic integrity. By training the model using an off-policy Reinforcement Learning algorithm, we optimize sequence length to minimize redundancy and enhance compression efficiency. Our method introduces an efficient and adaptive data compression system built upon advanced Reinforcement Learning techniques, functioning independently of external grammatical or world knowledge. This approach shows significant improvements in compression ratios compared to conventional methods. By leveraging the latent information within language models, our system effectively compresses data without requiring explicit content understanding, paving the way for more robust and practical compression solutions across various applications.