Many real-life scenarios require humans to make difficult trade-offs: do we always follow all the traffic rules or do we violate the speed limit in an emergency? These scenarios force us to evaluate the trade-off between collective norms and our own personal objectives. To create effective AI-human teams, we must equip AI agents with a model of how humans make trade-offs in complex, constrained environments. These agents will be able to mirror human behavior or to draw human attention to situations where decision making could be improved. To this end, we propose a novel inverse reinforcement learning (IRL) method for learning implicit hard and soft constraints from demonstrations, enabling agents to quickly adapt to new settings. In addition, learning soft constraints over states, actions, and state features allows agents to transfer this knowledge to new domains that share similar aspects. We then use the constraint learning method to implement a novel system architecture that leverages a cognitive model of human decision making, multi-alternative decision field theory (MDFT), to orchestrate competing objectives. We evaluate the resulting agent on trajectory length, number of violated constraints, and total reward, demonstrating that our agent architecture is both general and achieves strong performance. Thus we are able to capture and replicate human-like trade-offs from demonstrations in environments when constraints are not explicit.
翻译:许多现实生活情景要求人类作出困难的权衡:我们是否总是遵循所有交通规则,或者我们在紧急情况下是否违反速度限制?这些假设迫使我们评估集体规范与我们个人目标之间的权衡。为了创建有效的AI人类团队,我们必须为AI代理人员配备一个模型,说明人类如何在复杂、受限的环境中作出权衡。这些代理人员将能够反映人类的行为,或提请人类注意可以改进决策的情况。为此,我们提议了一种新的反向强化学习方法,以学习演示所隐含的硬性和软性限制,使代理人员能够迅速适应新的环境。此外,这些情景迫使我们评估集体规范与我们个人目标之间的权衡。为了建立有效的AI人类团队,我们必须使AI代理人员能够将这种知识转移到具有类似特点的新领域。然后,我们用约束学习方法实施一个新的系统架构,利用人类决策的认知模型、多选择的实地理论(MDFTFT)来协调相互竞争的目标。我们评估由此形成的代理人员在轨迹长度、被违反的限制数量和全部报酬方面的情况,表明我们的代理人员结构是普遍的,而不是在明显的环境上获得强大的表现。因此,我们可以复制和复制。