Social Choice with Changing Preferences: Representation Theorems and Long-Run Policies

• URL: http://arxiv.org/abs/2011.02544v1
• Date: Wed, 4 Nov 2020 21:21:04 GMT
• Title: Social Choice with Changing Preferences: Representation Theorems and Long-Run Policies
• Authors: Kshitij Kulkarni, Sven Neth
• Abstract summary: We show how representation theorems from social choice theory can be adapted to characterize optimal policies. We provide an axiomatic characterization of MDP reward functions that agree with the Utilitarianism social welfare functionals of social choice theory.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study group decision making with changing preferences as a Markov Decision Process. We are motivated by the increasing prevalence of automated decision-making systems when making choices for groups of people over time. Our main contribution is to show how classic representation theorems from social choice theory can be adapted to characterize optimal policies in this dynamic setting. We provide an axiomatic characterization of MDP reward functions that agree with the Utilitarianism social welfare functionals of social choice theory. We also provide discussion of cases when the implementation of social choice-theoretic axioms may fail to lead to long-run optimal outcomes.

Related papers

• Policy Aggregation [21.21314301021803]
  We consider the challenge of AI value alignment with multiple individuals with different reward functions and optimal policies in an underlying Markov decision process. We formalize this problem as one of policy aggregation, where the goal is to identify a desirable collective policy. Key insight is that social choice methods can be reinterpreted by identifying ordinal preferences with volumes of subsets of the state-action occupancy polytope.
  arXiv  Detail & Related papers  (2024-11-06T04:19:50Z)
• Representative Social Choice: From Learning Theory to AI Alignment [0.0]
  In representative social choice, the population is represented by a finite sample of individual-issue pairs based on which social choice decisions are made. We show that many of the deepest questions in representative social choice can be naturally formulated as statistical learning problems. We further formulates for representative social choice, and prove Arrow-like axioms with new tools of generalization analysis.
  arXiv  Detail & Related papers  (2024-10-31T14:07:26Z)
• Axioms for AI Alignment from Human Feedback [44.51306968484829]
  We develop novel rules for learning reward functions with strong axiomatic guarantees. A key innovation from the standpoint of social choice is that our problem has a linear structure.
  arXiv  Detail & Related papers  (2024-05-23T16:29:29Z)
• Average-Case Analysis of Iterative Voting [33.68929251752289]
  Iterative voting is a natural model of repeated strategic decision-making in social choice. Prior work has analyzed the efficacy of iterative plurality on the welfare of the chosen outcome at equilibrium. This work extends average-case analysis to a wider class of distributions and distinguishes when iterative plurality improves or degrades welfare.
  arXiv  Detail & Related papers  (2024-02-13T00:46:46Z)
• Causal Fairness for Outcome Control [68.12191782657437]
  We study a specific decision-making task called outcome control in which an automated system aims to optimize an outcome variable $Y$ while being fair and equitable. In this paper, we first analyze through causal lenses the notion of benefit, which captures how much a specific individual would benefit from a positive decision. We then note that the benefit itself may be influenced by the protected attribute, and propose causal tools which can be used to analyze this.
  arXiv  Detail & Related papers  (2023-06-08T09:31:18Z)
• Off-Policy Evaluation with Policy-Dependent Optimization Response [90.28758112893054]
  We develop a new framework for off-policy evaluation with a textitpolicy-dependent linear optimization response. We construct unbiased estimators for the policy-dependent estimand by a perturbation method. We provide a general algorithm for optimizing causal interventions.
  arXiv  Detail & Related papers  (2022-02-25T20:25:37Z)
• Temporal Abstraction in Reinforcement Learning with the Successor Representation [65.69658154078007]
  We argue that the successor representation (SR) can be seen as a natural substrate for the discovery and use of temporal abstractions. We show how the SR can be used to discover options that facilitate either temporally-extended exploration or planning.
  arXiv  Detail & Related papers  (2021-10-12T05:07:43Z)
• Efficient PAC Reinforcement Learning in Regular Decision Processes [99.02383154255833]
  We study reinforcement learning in regular decision processes. Our main contribution is to show that a near-optimal policy can be PAC-learned in time in a set of parameters.
  arXiv  Detail & Related papers  (2021-05-14T12:08:46Z)
• Towards a new Social Choice Theory [0.0]
  Social choice is the theory about collective decision towards social welfare starting from individual opinions, preferences, interests or welfare. The field of Computational Social Welfare is somewhat recent and it is gaining impact in the Artificial Intelligence Community. I want to introduce, following my Open Standardization and Open Integration Theory, as a global social goal of Social Choice Optimization.
  arXiv  Detail & Related papers  (2020-07-30T11:36:36Z)
• Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions [80.49176924360499]
  We establish a framework for directing a society of simple, specialized, self-interested agents to solve sequential decision problems. We derive a class of decentralized reinforcement learning algorithms. We demonstrate the potential advantages of a society's inherent modular structure for more efficient transfer learning.
  arXiv  Detail & Related papers  (2020-07-05T16:41:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.