arXiv：cs.AI· Mohammad Mahdi Samiei Paqaleh, Mehdi Jamalkhah, Mahdieh Soleymani Baghshah·· 23 小时前
VQEL：用智能体内部向量量化实现涌现语言博弈中的自博弈
VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization
AI 导读
VQEL 将向量量化引入消息生成过程，让智能体基于学习到的码本进行离散内部表征的自博弈，同时保持端到端可微。该码本自然形成符号词表，可在后续与其他智能体的互博弈中直接迁移和对齐。实验显示，经 VQEL 自博弈预训练的智能体在后续互博弈中符号对齐更一致、任务成功率更高。
正文
Abstract:Emergent Language (EL) focuses on the emergence of communication among artificial agents. Although symbolic communication channels more closely mirror the discrete nature of human language, learning such protocols remains fundamentally difficult due to the non-differentiability of symbol sampling. Existing approaches typically rely on high-variance gradient estimators such as REINFORCE or on continuous relaxations such as Gumbel-Softmax, both of which suffer from limitations in training stability and scalability. Motivated by cognitive theories that emphasize intrapersonal processes preceding communication, we explore self-play as a substrate for language emergence prior to mutual interaction. We introduce Vector Quantized Emergent Language (VQEL), a novel architecture that incorporates vector quantization into the message generation process. VQEL enables agents to perform self-play using discrete internal representations derived from a learned codebook while preserving end-to-end differentiability. Moreover, the resulting vector-quantized codebook naturally induces a symbolic vocabulary that can be directly transferred and aligned during subsequent mutual play with other agents. Empirical results show that agents pretrained via VQEL self-play achieve more consistent symbol alignment and higher task success when later engaged in mutual interaction. These findings position self-play as a principled and effective mechanism for learning discrete communication protocols, addressing key optimization and representational challenges in emergent language systems.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2503.04940 [cs.CL] |
| (or arXiv:2503.04940v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2503.04940 arXiv-issued DOI via DataCite |
|
| Journal reference: | Transactions on Machine Learning Research, August 2026 |
Submission history
From: Mohammad Mahdi Samiei Paqaleh [view email]
[v1]
Thu, 6 Mar 2025 20:15:51 UTC (795 KB)
[v2]
Sun, 22 Feb 2026 19:34:09 UTC (1,909 KB)
[v3]
Tue, 13 Oct 2026 15:31:45 UTC (4,303 KB)
来源：arXiv：cs.AI · arxiv.org