arXiv：cs.AI· Gongpu Chen, Deniz G\"und\"uz·· 18 小时前
将信息嵌入策略随机性：MDP 中的分布保持隐式通信
Embedding Information in Policy Randomness: Distribution-Preserving Implicit Communication in MDPs
AI 导读
研究者提出 posterior-matching randomness modulation（PRAM）编码方案，通过调制随机策略的动作实现将信息嵌入智能体行为，同时保持每个状态和消息下的预设动作分布不变，并证明随状态轨迹足够长可实现任意小错误概率解码。实验展示了该框架在多位策略水印和轨迹溯源中的应用。
正文
Abstract:This paper investigates a new role of randomness in stochastic policies--as a medium for embedding and communicating information. Specifically, we consider an agent interacting with an environment according to a prescribed stochastic policy. By carefully modulating the random action realizations of the policy, information can be embedded into the agent's behavior without altering the prescribed action distribution. We cast this problem as a channel coding problem, in which the controlled system implicitly serves as a communication channel. We then propose a coding scheme, termed posterior-matching randomness modulation (PRAM), that selects actions according to the message to be transmitted. With the aid of common randomness independent of the control system, PRAM preserves the prescribed action distribution for every state and every message. We further prove that PRAM is asymptotically reliable: the message can be decoded with arbitrarily small error probability as the observed state trajectory becomes sufficiently long. Experiments demonstrate the effectiveness of the proposed framework in applications including multi-bit policy watermarking and trajectory provenance.
| Comments: | 18 pages, 6 figures |
| Subjects: | Information Theory (cs.IT); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.15976 [cs.IT] |
| (or arXiv:2610.15976v1 [cs.IT] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15976 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gongpu Chen [view email]
[v1]
Sun, 11 Oct 2026 23:20:39 UTC (340 KB)
来源：arXiv：cs.AI · arxiv.org