HCMD-zero: Learning Value Aligned Mechanisms from Data

• URL: http://arxiv.org/abs/2202.10122v1
• Date: Mon, 21 Feb 2022 11:13:53 GMT
• Title: HCMD-zero: Learning Value Aligned Mechanisms from Data
• Authors: Jan Balaguer, Raphael Koster, Ari Weinstein, Lucy Campbell-Gillingham, Christopher Summerfield, Matthew Botvinick, Andrea Tacchetti
• Abstract summary: HCMD-zero is a general purpose method to construct mechanism agents. It learns by mediating interactions among participants, while remaining engaged in an electoral contest with copies of itself. Our results show that HCMD-zero produces competitive mechanism agents that are consistently preferred by human participants.
• Score: 11.146694178077565
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Artificial learning agents are mediating a larger and larger number of interactions among humans, firms, and organizations, and the intersection between mechanism design and machine learning has been heavily investigated in recent years. However, mechanism design methods make strong assumptions on how participants behave (e.g. rationality), or on the kind of knowledge designers have access to a priori (e.g. access to strong baseline mechanisms). Here we introduce HCMD-zero, a general purpose method to construct mechanism agents. HCMD-zero learns by mediating interactions among participants, while remaining engaged in an electoral contest with copies of itself, thereby accessing direct feedback from participants. Our results on the Public Investment Game, a stylized resource allocation game that highlights the tension between productivity, equality and the temptation to free-ride, show that HCMD-zero produces competitive mechanism agents that are consistently preferred by human participants over baseline alternatives, and does so automatically, without requiring human knowledge, and by using human data sparingly and effectively Our detailed analysis shows HCMD-zero elicits consistent improvements over the course of training, and that it results in a mechanism with an interpretable and intuitive policy.

Related papers

• Meta-Representational Predictive Coding: Biomimetic Self-Supervised Learning [51.22185316175418]
  We present a new form of predictive coding that we call meta-representational predictive coding (MPC) MPC sidesteps the need for learning a generative model of sensory input by learning to predict representations of sensory input across parallel streams.
  arXiv  Detail & Related papers  (2025-03-22T22:13:14Z)
• Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals [82.68757839524677]
  Interpretability research aims to bridge the gap between empirical success and our scientific understanding of large language models (LLMs) We propose a formulation of competition of mechanisms, which focuses on the interplay of multiple mechanisms instead of individual mechanisms. Our findings show traces of the mechanisms and their competition across various model components and reveal attention positions that effectively control the strength of certain mechanisms.
  arXiv  Detail & Related papers  (2024-02-18T17:26:51Z)
• Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation [50.01551945190676]
  Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. We propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures. We demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.
  arXiv  Detail & Related papers  (2024-01-22T18:58:22Z)
• Learning Multimodal Latent Dynamics for Human-Robot Interaction [19.803547418450236]
  This article presents a method for learning well-coordinated Human-Robot Interaction (HRI) from Human-Human Interactions (HHI) We devise a hybrid approach using Hidden Markov Models (HMMs) as the latent space priors for a Variational Autoencoder to model a joint distribution over the interacting agents. We find that Users perceive our method as more human-like, timely, and accurate and rank our method with a higher degree of preference over other baselines.
  arXiv  Detail & Related papers  (2023-11-27T23:56:59Z)
• A Human-Machine Joint Learning Framework to Boost Endogenous BCI Training [20.2015819836196]
  Endogenous brain-computer interfaces (BCIs) provide a direct pathway from the brain to external devices. mastering spontaneous BCI control requires the users to generate discriminative and stable brain signal patterns by imagery. Here, we propose a human-machine joint learning framework to boost the learning process in endogenous BCIs.
  arXiv  Detail & Related papers  (2023-08-25T01:24:18Z)
• Decentralized Adversarial Training over Graphs [55.28669771020857]
  The vulnerability of machine learning models to adversarial attacks has been attracting considerable attention in recent years. This work studies adversarial training over graphs, where individual agents are subjected to varied strength perturbation space.
  arXiv  Detail & Related papers  (2023-03-23T15:05:16Z)
• Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning [114.36124979578896]
  We design a dynamic mechanism using offline reinforcement learning algorithms. Our algorithm is based on the pessimism principle and only requires a mild assumption on the coverage of the offline data set.
  arXiv  Detail & Related papers  (2022-05-05T05:44:26Z)
• Distributed Reinforcement Learning for Robot Teams: A Review [10.92709534981466]
  Recent advances in sensing, actuation, and computation have opened the door to multi-robot systems. Community has leveraged model-free multi-agent reinforcement learning to devise efficient, scalable controllers for multi-robot systems. Recent findings: Decentralized MRS face fundamental challenges, such as non-stationarity and partial observability.
  arXiv  Detail & Related papers  (2022-04-07T15:34:19Z)
• The Good Shepherd: An Oracle Agent for Mechanism Design [6.226991885861965]
  We propose an algorithm for constructing agents that perform well when evaluated over the learning trajectory of their adaptive co-players. Our results show that our mechanisms are able to shepherd the participants strategies towards favorable outcomes.
  arXiv  Detail & Related papers  (2022-02-21T11:28:09Z)
• Human-Robot Collaboration and Machine Learning: A Systematic Review of Recent Research [69.48907856390834]
  Human-robot collaboration (HRC) is the approach that explores the interaction between a human and a robot. This paper proposes a thorough literature review of the use of machine learning techniques in the context of HRC.
  arXiv  Detail & Related papers  (2021-10-14T15:14:33Z)
• Human Trajectory Forecasting in Crowds: A Deep Learning Perspective [89.4600982169]
  We present an in-depth analysis of existing deep learning-based methods for modelling social interactions. We propose two knowledge-based data-driven methods to effectively capture these social interactions. We develop a large scale interaction-centric benchmark TrajNet++, a significant yet missing component in the field of human trajectory forecasting.
  arXiv  Detail & Related papers  (2020-07-07T17:19:56Z)

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.