Skip to content

State-based Selection of Expert Policies in Disaster Environments and Reinforcement Learning of a Unified Student Policy via Distillation

Sep 2026 · Transactions of the Korean Society of Mechanical Engineers A

Abstract

본 논문은 재난 환경에서 4족 보행 로봇의 보행, 전도복귀 및 낙하착지를 단일 정책으로 통합하기 위한 제어 프레임워크를 제안한다. 기존의 단일 정책 공동 학습 방식은 상이한 목표를 동시에 다루는 과정에서 학습 시간과 난이도가 증가할 수 있으며, finite state machine(FSM) 기반 다중 정책 전환 방식은 모드 선택 및 전환 규칙에 의존한다. 이를 해결하기 위해 보행, 전도복귀, 낙하착지에 특화된 세 교사 정책을 학습하고, 로봇 상태에 따라 적절한 교사 행동을 선택하여 단일 학생 정책으로 증류하는 방법을 연구하였다. Isaac Sim 및 Isaac Lab 환경에서 학습한 정책을 MuJoCo 기반 복합 시나리오에서 sim-to-sim 방식으로 평가한 결과, 제안 방법은 단일 정책 공동 학습 및 FSM 기반 방법과 비교하여 더 높은 평균 성공률을 보였으며, 시나리오 수행 시 명시적 정책 스위칭 없이 세 기술을 단일 정책으로 통합할 수 있음을 검증하였다.

View source

Similar papers

#machine learning Review Open access Oct 2014

Software development in startup companies: A systematic mapping study

The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.

Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al. · 394 citations · ⚡54
#machine learning Review Open access Jun 2014

Why Early-Stage Software Startups Fail: A Behavioral Framework

This state-of-practice investigation was performed using a literature review followed by a multiple-case study approach and presents how inconsistency between managerial strategies and execution can lead to failure by means of a behavioral framework.

Carmine Giardino, Xiaofeng Wang, P. Abrahamsson · 175 citations · ⚡19
#machine learning Review Open access Oct 2016

“Failures” to be celebrated: an analysis of major pivots of software startups

This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.

Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al. · 127 citations · ⚡15
#machine learning Review Open access May 2016

Key Challenges in Software Startups Across Life Cycle Stages

It is found that what perceived as biggest challenges by software startups do vary across different life cycle stages, even though its significance decreases when the learning focuses of the startups move from problem to solution and their products mature.

Xiaofeng Wang, Henry Edison, Sohaib Shahid Bajwa et al. · 62 citations · ⚡6

Related blog posts

Microsoft Research Blog Oct 12, 2026

Simulating student learning for better AI tutoring

StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.

MIT News · Artificial Intelligence Oct 7, 2026

Discovering the value of humanistic inquiry

Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.