Memory Is Communication: The Frontier Between Remembering and Signaling

记忆即通信：记忆与信号传递之间的边界

Abstract: A bounded agent may obtain information for a decision from its own past, from peers, or from both sources. Retaining task-relevant history can reduce later communication, while a peer message can supply what memory lacks. Under limits on both resources, how should an agent allocate its information budget?

摘要： 一个受限智能体可以通过自身过去的信息、同伴的信息或两者结合来获取决策所需的信息。保留与任务相关的历史记录可以减少后续的通信需求，而来自同伴的消息则可以弥补记忆的不足。在两种资源都受限的情况下，智能体应如何分配其信息预算？

Given a fixed task and decision rule, the memory and message rate pairs attaining a performance threshold form an achievable region under specified rules for using history and peer observations. We call its efficient boundary the remembering—signaling frontier.

在给定的任务和决策规则下，达到特定性能阈值的记忆与消息速率对，在预设的历史记录和同伴观察使用规则下，构成了一个可实现区域。我们将该区域的有效边界称为“记忆-信号传递边界”（remembering—signaling frontier）。

Across conditions where history permits the same maximum reduction in task loss, we hypothesize that a bounded agent will need less peer communication when it obtains a larger loss reduction from history. In preliminary referential games, target repetition coincided with shorter successful messages, while predictability from a hidden cyclic rule did not shorten them. Experiments varying memory and message rates can estimate the frontier and test this prediction across cooperative tasks.

在历史记录能够实现相同最大任务损失降低的条件下，我们假设：当受限智能体从历史记录中获得的损失降低幅度越大时，其所需的同伴通信就越少。在初步的指称博弈（referential games）中，目标重复与更短的成功消息相关联，而基于隐藏循环规则的可预测性则并未缩短消息长度。通过改变记忆和消息速率的实验，可以估算该边界，并在协作任务中验证这一预测。