论文标题
熔炉2.0
Melting Pot 2.0
论文作者
论文摘要
多代理人工智能研究有望开发一条发展智能技术的途径，这些技术比“ solipsistic”方法所产生的智能技术更像是人类，并且更具人为兼容的方法，而“ solipsistic”方法不考虑代理之间的相互作用。熔炉是一种开发的研究工具，旨在促进多代理人工智能的工作，并提供了一项评估协议，该协议在一组规范的测试场景中对新型社会伙伴进行概括。每个场景将物理环境（“基板”）与参考人群（“背景人群”）配对，以创建一个社会状况，并在所涉及的个人之间具有很大的相互依存关系。例如，某些场景的灵感来自基于机构 - 经济学的自然资源管理和公共善良困境的叙述。其他人的灵感来自进化生物学，游戏理论和人造生活的考虑。熔炉旨在涵盖最大多样化的相互依存和激励措施。它包括完全竞争（零和零）动机和完全合作（共享奖励）动机的极端案例，但并没有停止。与现实生活中一样，熔炉中的大部分场景都具有混合的激励措施。他们既不纯粹是竞争性的，也不是纯粹的合作者，因此要求成功的代理人能够驾驭所产生的歧义。在这里，我们描述了熔炉2.0，它修改并扩展了熔炉。我们还引入了对场景不对称角色的支持，并解释了如何将它们集成到评估协议中。该报告还包含：（1）所有基材和方案的详细信息； （2）所有基线算法和结果的完整描述。我们的目的是让使用Medting Pot 2.0作为研究人员的参考。
Multi-agent artificial intelligence research promises a path to develop intelligent technologies that are more human-like and more human-compatible than those produced by "solipsistic" approaches, which do not consider interactions between agents. Melting Pot is a research tool developed to facilitate work on multi-agent artificial intelligence, and provides an evaluation protocol that measures generalization to novel social partners in a set of canonical test scenarios. Each scenario pairs a physical environment (a "substrate") with a reference set of co-players (a "background population"), to create a social situation with substantial interdependence between the individuals involved. For instance, some scenarios were inspired by institutional-economics-based accounts of natural resource management and public-good-provision dilemmas. Others were inspired by considerations from evolutionary biology, game theory, and artificial life. Melting Pot aims to cover a maximally diverse set of interdependencies and incentives. It includes the commonly-studied extreme cases of perfectly-competitive (zero-sum) motivations and perfectly-cooperative (shared-reward) motivations, but does not stop with them. As in real-life, a clear majority of scenarios in Melting Pot have mixed incentives. They are neither purely competitive nor purely cooperative and thus demand successful agents be able to navigate the resulting ambiguity. Here we describe Melting Pot 2.0, which revises and expands on Melting Pot. We also introduce support for scenarios with asymmetric roles, and explain how to integrate them into the evaluation protocol. This report also contains: (1) details of all substrates and scenarios; (2) a complete description of all baseline algorithms and results. Our intention is for it to serve as a reference for researchers using Melting Pot 2.0.
