We present a general framework for evolutionary learning to emergent unbiased state representation without any supervision. Evolutionary frameworks such as self-play converge to bad local optima in case of multi-agent reinforcement learning in non-cooperative partially observable environments with communication due to information asymmetry. Our proposed framework is a simple modification of self-play inspired by mechanism design, also known as {\em reverse game theory}, to elicit truthful signals and make the agents cooperative. The key idea is to add imaginary rewards using the peer prediction method, i.e., a mechanism for evaluating the validity of information exchanged between agents in a decentralized environment. Numerical experiments with predator prey, traffic junction and StarCraft tasks demonstrate that the state-of-the-art performance of our framework.

翻译：我们提出了一种通用演化学习框架，可在无监督条件下涌现无偏状态表征。在非合作部分可观测环境中，具有通信机制的多智能体强化学习中，自我博弈等演化框架会因信息不对称而收敛至不良局部最优。受机制设计（亦称逆向博弈论）启发，本文提出的框架对自我博弈进行了简单改进，旨在激发真实信号并促使智能体合作。其核心思想是利用同伴预测方法（即在去中心化环境中评估智能体间信息交换有效性的机制）添加虚拟奖励。在捕食者-猎物、交通枢纽及星际争霸任务上的数值实验表明，本框架达到了当前最优性能。