EMOTE：一种通过共情对他人进行建模的可解释架构
EMOTE: An Explainable architecture for Modelling the Other Through Empathy
AI总结：
本文提出EMOTE架构，通过学习“想象网络”将其他智能体的观测状态转换为人类可解释的共情状态，从而在固定策略多智能体场景中更稳健地建模他人动作价值函数并提升博弈性能。
摘要：
我们通常可以假设他人拥有与我们自身类似的目标。这一假设有时也可应用于多智能体博弈——例如，智能体1对绿色小球的偏好类似于智能体2对红色小球的偏好。这种“类比”假设与被称为共情的认知过程密切相关。受共情启发，我们设计了一种简单且可解释的架构，用于对另一个智能体的动作价值函数进行建模。该方法涉及学习一个“想象网络”（Imagination Network），用于转换所观察到的另一个智能体的状态，从而生成人类可解释的“共情状态”（empathetic state）；当该状态被呈现给学习智能体时，会产生模仿另一个智能体的行为。我们的方法适用于由单个学习智能体和按照固定策略行动的其他（独立）智能体组成的多智能体场景。该架构对于使用复合价值函数或奖励函数的算法尤其有益（但不限于此）。我们表明，我们的方法在多智能体博弈中取得了更好的性能，能够在不同环境配置下稳健地估计其他智能体的模型。此外，我们表明共情状态是人类可解释的，因此也是可验证的。
英文摘要：
We can usually assume others have goals analogous to our own. This assumption can also, at times, be applied to multi-agent games - e.g. Agent 1's attraction to green pellets is analogous to Agent 2's attraction to red pellets. This "analogy" assumption is tied closely to the cognitive process known as empathy. Inspired by empathy, we design a simple and explainable architecture to model another agent's action-value function. This involves learning an "Imagination Network" to transform the other agent's observed state in order to produce a human-interpretable "empathetic state" which, when presented to the learning agent, produces behaviours that mimic the other agent. Our approach is applicable to multi-agent scenarios consisting of a single learning agent and other (independent) agents acting according to fixed policies. This architecture is particularly beneficial for (but not limited to) algorithms using a composite value or reward function. We show our method produces better performance in multi-agent games, where it robustly estimates the other's model in different environment configurations. Additionally, we show that the empathetic states are human interpretable, and thus verifiable.
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。
