paper-with-me

Papers

What Would Jiminy Cricket Do? Towards Agents That Behave Morally

2021-10-25 · Dan Hendrycks, Mantas Mazeika, Andy Zou, Sahil Patel, Christine Zhu, Jesus Navarro, Dawn Song, Bo Li, Jacob Steinhardt

When making everyday decisions, people are guided by their conscience, an internal sense of right and wrong. By contrast, artificial agents are currently not endowed with a moral sense. As a consequence, they may learn to behave immorally when trained on environments that ignore moral concerns, such as violent video games. With the advent of generally capable agents that pretrain on many environments, it will become necessary to mitigate inherited biases from environments that teach immoral behavior. To facilitate the development of agents that avoid causing wanton harm, we introduce Jiminy Cricket, an environment suite of 25 text-based adventure games with thousands of diverse, morally salient scenarios. By annotating every possible game state, the Jiminy Cricket environments robustly evaluate whether agents can act morally while maximizing reward. Using models with commonsense moral knowledge, we create an elementary artificial conscience that assesses and guides agents. In extensive experiments, we find that the artificial conscience approach can steer agents towards moral behavior without sacrificing performance.

📄 PDF Abstract BibTeX arXiv:2110.13136

Code (1)

hendrycks/jiminy-cricket 공식 구현 jax

Similar Papers 제목 키워드 기반

Aligning to Social Norms and Values in Interactive Narratives

2022-05-04 · NAACL 2022 7 · Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi 외

We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games -- environments wherein an agent perceives and interacts with a world through natu…

text-based games

The Jiminy Advisor: Moral Agreements Among Stakeholders Based on Norms and Argumentation

2018-12-11 · Beishui Liao, Pere Pardo, Marija Slavkovik, Leendert van der Torre

An autonomous system is constructed by a manufacturer, operates in a society subject to norms and laws, and interacts with end users. All of these actors are stakeholders affected by the behavior of the autonomous system…

Decision Making

Strangers to Themselves: What Language Models Say About Themselves Is Generic

2026-09-09 · Phil Blandfort, Urja Pawar arxiv

Language models can fluently describe how they would behave: whether they would cave to pushback, misuse a tool, or lie under pressure. Is that description actually about the model speaking? We turn self-knowledge into a…

You Cannot Do That Ben Stokes: Dynamically Predicting Shot Type in Cricket Using a Personalized Deep Neural Network

2021-02-03 · Will Gürpınar-Morgan, Daniel Dinsdale, Joe Gallagher, Aditya Cherukumudi 외

The ability to predict what shot a batsman will attempt given the type of ball and match situation is both one of the most challenging and strategically important tasks in cricket. The goal of the batsman is to score as …

Decision Making

Evaluating and Modelling Hanabi-Playing Agents

2017-04-24 · Joseph Walton-Rivers, Piers R. Williams, Richard Bartle, Diego Perez-Liebana 외

Agent modelling involves considering how other agents will behave, in order to influence your own actions. In this paper, we explore the use of agent modelling in the hidden-information, collaborative card game Hanabi. W…

Game of Hanabi