Classical imitation learning methods suffer substantially from the learning hierarchical policies when the imitative agent faces an unobserved state by the expert agent. To address these drawbacks, we propose an online active learning through active inference approach that encodes the expert's demonstrations based on observation-action to improve the learner's future motion prediction. For this purpose, we provide a switching Dynamic Bayesian Network based on the dynamic interaction between the expert agent and another object in its surrounding as a reference model, which we exploit to initialize an incremental probabilistic learning model. This learning model grows and matures based on the freeenergy formulation and message passing of active inference dynamically at discrete and continuous levels in an online active learning phase. In this scheme, generalized states of the learning world are represented as distance-vector, where it is the learner's observation concerning its interaction with a moving object. Considering the distance vector entail intentions, it enables action prediction evaluation in a prospective sense. We illustrate these points using simulations of driving intelligent agents. The learning agent is trained by using long-term predictions from the generative learning model to reproduce the expert's motion while learning how to select a suitable action through new experiences. Our results affirm that a Dynamic Bayesian optimal approach provides a principled framework and outperforms conventional reinforcement learning methods. Furthermore, it endorses the general formulation of action prediction as active inference.
While surgical videos are valuable support material for activities around surgery, their summarization demands great amounts of time from surgeons, resulting in the production of very few videos. We study the practices involving surgical video to motivate and inform the future design of tools for their summarization. Through interviews and observations in a feld study, we fnd that (1) video summaries provide an important support for surgery, being used for self-improvement, education, discussing cases, scientifc research, patient communication and as legal resources; (2) video summarization follows a process hindered by the loss of knowledge that originates during recording; and, (3) surgeons develop ad-hoc coordination strategies which involve using the video itself for articulation work, making it both the feld of work and coordination artifact. We discuss ways in which tools can facilitate capturing knowledge during live action using these strategies.CCS Concepts: • Human-centered computing → Empirical studies in HCI.
This paper proposes an adaptive method to enable imitation learning from expert demonstrations in a multi-agent context. Our work employs the inverse reinforcement learning method to a coupled Dynamic Bayesian Network to facilitate dynamic learning in an interactive system. This method studies the interaction at both discrete and continuous levels by identifying inter-relationships between the objects to facilitates the prediction of an expert agent's demonstrations. We evaluate the learning procedure in the scene of learner agent based on probabilistic reward function. Our goal is to estimate policies that predicted trajectories match the observed one by minimizing the Kullback-Leiber divergence. The reward policies provide a probabilistic dynamic structure to minimize the abnormalities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.