An official website of the United States government
Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take action against an undesirable outcome made by an algorithmic system, is receiving growing attention. The bulk of the literature on algorithmic recourse to-date focuses primarily on how to provide recourse to a single individual, overlooking a critical element: the effects of a continuously changing context. Disregarding these effects on recourse is a significant oversight, since, in almost all cases, recourse consists of an individual making a first, unfavorable attempt, and then being given an opportunity to make one or several attempts at a later date — when the context might have changed. This can create false expectations, as initial recourse recommendations may become less reliable over time due to model drift and competition for access to the favorable outcome between individuals. In this work we propose an agent-based simulation framework for studying the effects of a continuously changing environment on algorithmic recourse. In particular, we identify two main effects that can alter the reliability of recourse for individuals represented by the agents: (1) competition with other agents acting upon recourse, and (2) competition with new agents entering the environment. Our findings highlight that only a small set of specific parameterizations result in algorithmic recourse that is reliable for agents over time. Consequently, we argue that substantial additional work is needed to understand recourse reliability over time, and to develop recourse methods that reward agents’ effort.
more »
« less
Blameworthiness in multi-agent settings
We provide a formal definition of blameworthiness in settings where multiple agents can collaborate to avoid a negative outcome. We first provide a method for ascribing blameworthiness to groups relative to an epistemic state (a distribution over causal models that describe how the outcome might arise). We then show how we can go from an ascription of blameworthiness for groups to an ascription of blameworthiness for individuals using a standard notion from cooperative game theory, the Shapley value. We believe that getting a good notion of blameworthiness in a group setting will be critical for designing autonomous agents that behave in a moral manner.
more »
« less
- PAR ID:
- 10093615
- Date Published:
- Journal Name:
- Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)It is common in online markets for agents to learn from other's actions. Such observational learning can lead to herding or information cascades in which agents eventually "follow the crowd". Models for such cascades have been well studied for Bayes-rational agents that choose pay-off optimal actions. In this paper, we additionally consider the presence of fake agents that seek to influence other agents into taking one particular action. To that end, these agents take a fixed action in order to influence the subsequent agents towards their preferred action. We characterize how the fraction of such fake agents impacts behavior of the remaining agents and show that in certain scenarios, an increase in the fraction of fake agents in fact reduces the chances of their preferred outcome.more » « less
-
“Big data” gives markets access to previously unmeasured characteristics of individual agents. Policymakers must decide whether and how to regulate the use of this data. We study how new data affects incentives for agents to exert effort in settings such as the labor market, where an agent's quality is initially unknown but is forecast from an observable outcome. We show that measurement of a new covariate has a systematic effect on the average effort exerted by agents, with the direction of the effect determined by whether the covariate is informative about long‐run quality versus a shock to short‐run outcomes. For a class of covariates satisfying a statistical property that we callstrong homoskedasticity, this effect is uniform across agents. More generally, new measurements can impact agents unequally, and we show that these distributional effects have a first‐order impact on social welfare.more » « less
-
null (Ed.)This work investigates how social agents can be designed to create a sense of ownership over them within a group of users. Social agents, such as conversational agents and chatbots, currently interact with people in impersonal, isolated, and often one-on-one interactions: one user and one agent. This is likely to change as agents become more socially sophisticated and integrated in social fabrics. Previous research has indicated that understanding who owns an agent can assist in creating expectations and understanding who an agent is accountable to within a group. We present findings from a three week case-study in which we implemented a chatbot that was successful in creating a sense of collective ownership within a community. We discuss the design choices that led to this outcome and implications for social agent design.more » « less
-
Machine learning models now automate decisions in applications where we may wish to provide recourse to adversely affected individuals. In practice, existing methods to provide recourse return actions that fail to account for latent characteristics that are not captured in the model (e.g., age, sex, marital status). In this paper, we study how the cost and feasibility of recourse can change across these latent groups. We introduce a notion of group-level plausibility to identify groups of individuals with a shared set of latent characteristics. We develop a general-purpose clustering procedure to identify groups from samples. Further, we propose a constrained optimization approach to learn models that equalize the cost of recourse over latent groups. We evaluate our approach through an empirical study on simulated and real-world datasets, showing that it can produce models that have better performance in terms of overall costs and feasibility at a group level.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
