翻译Neuralese
Translating Neuralese
摘要：
最近已经提出了几种方法来学习通过可区分的通信信道进行协调的分散式深度多智能体策略。虽然这些政策对许多任务都是有效的，但对其诱导传播策略的解释仍然是一个挑战。在这里，我们建议通过翻译来解释代理的消息。与典型的机器翻译问题不同，我们没有并行数据可供学习。相反，我们开发了一个翻译模型的基础上的洞察力，代理消息和自然语言字符串意味着相同的事情，如果他们诱导相同的信念在一个听众的世界。我们提出的理论保证和经验证据表明，我们的方法保留了语义和语用的消息，确保通过翻译层进行通信的球员不会遭受实质性的损失，相对于球员的奖励与共同的语言。
英文摘要：
Several approaches have recently been proposed for learning decentralized deep multiagent policies that coordinate via a differentiable communication channel. While these policies are effective for many tasks, interpretation of their induced communication strategies has remained a challenge. Here we propose to interpret agents' messages by translating them. Unlike in typical machine translation problems, we have no parallel data to learn from. Instead we develop a translation model based on the insight that agent messages and natural language strings mean the same thing if they induce the same belief about the world in a listener. We present theoretical guarantees and empirical evidence that our approach preserves both the semantics and pragmatics of messages by ensuring that players communicating through a translation layer do not suffer a substantial loss in reward relative to players with a common language.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
