Connections between Relational Event Model and Inverse Reinforcement Learning for Characterizing Group Interaction Sequences

• URL: http://arxiv.org/abs/2010.09810v1
• Date: Mon, 19 Oct 2020 19:40:29 GMT
• Title: Connections between Relational Event Model and Inverse Reinforcement Learning for Characterizing Group Interaction Sequences
• Authors: Congyu Wu
• Abstract summary: We explore previously unidentified connections between relational event model (REM) and inverse reinforcement learning (IRL) REM is a conventional approach to tackle such a problem whereas the application of IRL is a largely unbeaten path. We demonstrate the special utility of IRL in characterizing group social interactions with an empirical experiment.
• Score: 0.18275108630751835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper we explore previously unidentified connections between relational event model (REM) from the field of network science and inverse reinforcement learning (IRL) from the field of machine learning with respect to their ability to characterize sequences of directed social interaction events in group settings. REM is a conventional approach to tackle such a problem whereas the application of IRL is a largely unbeaten path. We begin by examining the mathematical components of both REM and IRL and find straightforward analogies between the two methods as well as unique characteristics of the IRL approach. We demonstrate the special utility of IRL in characterizing group social interactions with an empirical experiment, in which we use IRL to infer individual behavioral preferences based on a sequence of directed communication events from a group of virtual-reality game players interacting and cooperating to accomplish a shared goal. Our comparison and experiment introduce fresh perspectives for social behavior analytics and help inspire new research opportunities at the nexus of social network analysis and machine learning.

Related papers

• Visual-Geometric Collaborative Guidance for Affordance Learning [63.038406948791454]
  We propose a visual-geometric collaborative guided affordance learning network that incorporates visual and geometric cues. Our method outperforms the representative models regarding objective metrics and visual quality.
  arXiv  Detail & Related papers  (2024-10-15T07:35:51Z)
• Federated Learning of Socially Appropriate Agent Behaviours in Simulated Home Environments [6.284099600214928]
  Social robots are increasingly integrated into daily life, ensuring their behaviours align with social norms is crucial. It is important to explore Federated Learning (FL) settings where individual robots can learn about their unique environments. We present a novel FL benchmark that evaluates different strategies, using multi-label regression objectives.
  arXiv  Detail & Related papers  (2024-03-12T12:16:40Z)
• Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents [18.961470450132637]
  This paper emphasizes the importance of spontaneous phenomena, wherein agents deeply engage in contexts and make adaptive decisions without explicit directions. We explored spontaneous cooperation across three competitive scenarios and successfully simulated the gradual emergence of cooperation.
  arXiv  Detail & Related papers  (2024-02-19T18:00:53Z)
• 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)
• SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction [19.075215661355486]
  We build a new anglebased trainable social interaction representation, named SocialCircle, for continuously reflecting the context of social interactions. We validate the effect of the proposed SocialCircle by training it along with several newly released trajectory prediction models. Experiments show that the SocialCircle not only quantitatively improves the prediction performance, but also qualitatively helps better simulate social interactions.
  arXiv  Detail & Related papers  (2023-10-09T02:59:21Z)
• Flexible social inference facilitates targeted social learning when rewards are not observable [58.762004496858836]
  Groups coordinate more effectively when individuals are able to learn from others' successes. We suggest that social inference capacities may help bridge this gap, allowing individuals to update their beliefs about others' underlying knowledge and success from observable trajectories of behavior.
  arXiv  Detail & Related papers  (2022-12-01T21:04:03Z)
• Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A Survey [71.43956423427397]
  We aim to identify the nonverbal cues and computational methodologies resulting in effective performance. This survey differs from its counterparts by involving the widest spectrum of social phenomena and interaction settings. Some major observations are: the most often used nonverbal cue, computational method, interaction environment, and sensing approach are speaking activity, support vector machines, and meetings composed of 3-4 persons equipped with microphones and cameras, respectively.
  arXiv  Detail & Related papers  (2022-07-20T13:37:57Z)
• Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior [0.0]
  We integrate social' interactions into the MARL setup through a user-defined relational network. We examine the effects of agent-agent relations on the rise of emergent behaviors.
  arXiv  Detail & Related papers  (2022-07-12T23:27:42Z)
• PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception [50.551003004553806]
  We create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions. Phase is validated with human experiments demonstrating that humans perceive rich interactions in the social events. As a baseline model, we introduce a Bayesian inverse planning approach, SIMPLE, which outperforms state-of-the-art feed-forward neural networks.
  arXiv  Detail & Related papers  (2021-03-02T18:44:57Z)
• 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.