960 Hits in 4.2 sec

Offline Preference-Based Apprenticeship Learning [article]

Daniel Shin, Daniel S. Brown, Anca D. Dragan
2022 arXiv   pre-print
We propose an approach that uses an offline dataset to craft preference queries via pool-based active learning, learns a distribution over reward functions, and optimizes a corresponding policy via offline  ...  To test our approach, we identify a subset of existing offline RL benchmarks that are well suited for offline reward learning and also propose new offline apprenticeship learning benchmarks which allow  ...  Toward this goal we propose OPAL: Offline Preference-based Apprenticeship Learning.  ... 
arXiv:2107.09251v3 fatcat:szmstp3xpramppumkdxgqwwpcm

Student Preference and Perception towards Online Education in Hyderabad City

Mr. Anjum Pasha, Jarupla Gorya
2019 International Journal of Trend in Scientific Research and Development  
Whereas new way of getting education is online education/ virtual education/ E-learning. Like shopping sites, internet also made easier to get education via online.  ...  In our research most of people preferred mode of education is online/e-learning/virtual way and only 26% people preferred offline education.  ...  Most people think that online education is an effective way of learning and some people prefer offline education.  ... 
doi:10.31142/ijtsrd22876 fatcat:l52ptbrgfnc2zhlvhplpzsdjgu

Scalable Bayesian Inverse Reinforcement Learning [article]

Alex J. Chan, Mihaela van der Schaar
2021 arXiv   pre-print
imitation learning algorithms.  ...  In this paper we introduce our method, Approximate Variational Reward Imitation Learning (AVRIL), that addresses both of these issues by jointly learning an approximate posterior distribution over the  ...  APPROACHING APPRENTICESHIP AND IMITATION OFFLINE Preliminaries.  ... 
arXiv:2102.06483v2 fatcat:jjm3ggfhzbae3cloknbfzeotue

A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization [article]

Pamul Yadav, Ashutosh Mishra, Junyong Lee, Shiho Kim
2022 arXiv   pre-print
Deep Reinforcement Learning (DRL) aims to create intelligent agents that can learn to solve complex problems efficiently in a real-world environment.  ...  This paper presents a survey on the recent developments in DRL-based approaches for adaptation and generalization. We begin by formulating these goals in the context of task and domain.  ...  Offline Reinforcement Learning (Offline-RL) Offline-RL enables policy learning from a pre-collected dataset of trajectories/experiences for the tasks/domains where the agent is not allowed to interact  ... 
arXiv:2202.08444v1 fatcat:xc3bgq3jdngazlplw66ejtax6q

A Survey on Reinforcement Learning for Recommender Systems [article]

Yuanguo Lin, Yong Liu, Fan Lin, Lixin Zou, Pengcheng Wu, Wenhua Zeng, Huanhuan Chen, Chunyan Miao
2022 arXiv   pre-print
Empirical results show that RL-based recommendation methods often surpass most of supervised learning methods, owing to the interactive nature and autonomous learning ability.  ...  In particular, Reinforcement Learning (RL) based recommender systems have become an emerging research topic in recent years.  ...  For example, apprenticeship learning via IRL algorithm [96] highlights the need for learning from an expert, which maximizes a reward based on a linear combination of known features.  ... 
arXiv:2109.10665v2 fatcat:wx5ghn66hzg7faxee54jf7gspq

Using process data to generate an optimal control policy via apprenticeship and reinforcement learning

Max R. Mowbray, Robin Smith, Ehecatl A. Del Rio‐Chanona, Dongda Zhang
2021 AIChE Journal  
The framework is demonstrated on three case studies, showing its potential for chemical process control. apprenticeship learning, inverse reinforcement learning, machine learning, optimal control, reinforcement  ...  First, we employ apprenticeship learning via inverse RL to analyze historical process data for synchronous identification of a reward function and parameterization of the control policy.  ...  This concept is generally termed as apprenticeship learning (AL).  ... 
doi:10.1002/aic.17306 fatcat:g3vdaqqhqjfmjfiklhv4pgpowm

Multiagent Stochastic Planning With Bayesian Policy Recognition

Alessandro Panella
To perform this task, I adopt Bayesian learning algorithms based on nonparametric prior distributions, that provide the flexibility required to infer models of unknown complexity.  ...  In my thesis work, I propose methodologies for learning the policy of external agents from their observed behavior, in the form of finite state controllers.  ...  Combining the latter with online FSC learning would lead to a preference elicitation methodology.  ... 
doi:10.1609/aaai.v27i1.8506 fatcat:2oaemt3wijhvxfsay4bztw6kxe

Exploring Apprenticeship Learning for Player Modelling in Interactive Narratives

Jessica Rivera-Villicana, Fabio Zambetta, James Harland, Marsha Berry
2019 Extended Abstracts of the Annual Symposium on Computer-Human Interaction in Play Companion Extended Abstracts - CHI PLAY '19 Extended Abstracts  
In this paper we present an early Apprenticeship Learning approach to mimic the behaviour of different players in a short adaption of the interactive fiction Anchorhead.  ...  We used Receding Horizon IRL (RHIRL) to learn players' goals in the form of reward functions, and derive policies to imitate their behaviour.  ...  Action representation and transition model We embedded the mechanics of the Anchorhead engine in the MDP module to perform the learning tasks offline.  ... 
doi:10.1145/3341215.3356314 dblp:conf/chiplay/Rivera-Villicana19 fatcat:pkh7zgnli5bspiq3vkc543zbvq

A Ranking Game for Imitation Learning [article]

Harshit Sikchi, Akanksha Saran, Wonjoon Goo, Scott Niekum
2022 arXiv   pre-print
This game encompasses a large subset of both inverse reinforcement learning (IRL) methods and methods which learn from offline preferences.  ...  We propose a new framework for imitation learning - treating imitation as a two-player ranking-based Stackelberg game between a policy and a reward function.  ...  Learning purely from offline rankings in manipulation environments We compare with the ability of a prior method -TREX (Brown et al., 2019) that learns purely from suboptimal preferences.  ... 
arXiv:2202.03481v1 fatcat:5eue7bjio5baflnlxlbqfbn6km

Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations [article]

Rohan Paleja, Andrew Silva, Letian Chen, Matthew Gombolay
2021 arXiv   pre-print
What is critically needed is the ability to extract this domain knowledge in a heterogeneous and interpretable apprenticeship learning framework to scale beyond the power of a single human expert, a necessity  ...  To perform this job, domain experts leverage heterogeneous strategies and rules-of-thumb honed over years of apprenticeship.  ...  Based upon the insight in prior work in homogeneous apprenticeship scheduling [14] that counterfactual reasoning was critical for learning scheduling strategies from demonstration, we adopt counterfactual  ... 
arXiv:1906.06397v5 fatcat:thqmemuqjzcpdifn36zow4n6he


MF. Arrozi, Arief Kusuma AP, Erry Yudhya Mulyani, Rian Adi Pamungkas, Ummanah
2022 International Journal of Education and Social Science Research  
The results showed that the student's perceptions of the implementation of the MBKM program were effectively based on the expectations of students.  ...  The research object is the policy of independent learning on an independent campus.  ...  A brief description of student perceptions based on their preferred preferences for the performance of MBKM is shown in table 3 .  ... 
doi:10.37500/ijessr.2022.5202 fatcat:yj4pxsyobncerbk4tuczaf2bga

Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions [article]

Tom Bewley, Freddy Lecue
2021 arXiv   pre-print
One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward function is inferred from sparse human feedback.  ...  We propose an online, active preference learning algorithm that constructs reward functions with the intrinsically interpretable, compositional structure of a tree.  ...  Apprenticeship learning via inverse 2017. A survey of preference-based reinforcement learning methods. Journal of reinforcement learning.  ... 
arXiv:2112.11230v1 fatcat:q7k5whnma5frhlo3ojowf5r4zy

Learning to Schedule Deadline- and Operator-Sensitive Tasks [article]

Hanan Rosemarin and John P. Dickerson and Sarit Kraus
2017 arXiv   pre-print
Next, we design a scalable machine-learning-based teleoperator-aware task scheduling algorithm and show, experimentally, that it performs well when compared to an omniscient optimal scheduling algorithm  ...  Gombolay et al. [2016] take a reinforcement learning approach to the apprenticeship problem, that is, learning human-quality heuristics; they do this by way of a pairwise ranking function, as we do, but  ...  Building on this, Section 3.3 gives RANKING, our learning-based online scheduling algorithm.  ... 
arXiv:1706.06051v1 fatcat:uxhrs753yrcyjovvd74oeqmkua

Teaching technology with technology: approaches to bridging learning and teaching gaps in simulation-based programming education

Md Golam Jamil, Sakirulai Olufemi Isiaq
2019 International Journal of Educational Technology in Higher Education  
To address the gap, this study facilitates an evidence-driven discussion on learning and teaching, as well as their relationship, in simulation-based programming education.  ...  The findings have provided fresh insights on several enabling and challenging aspects of simulation-based programming education.  ...  The authors also like to thank Solent University's Learning and Teaching Institute (SLTI) for funding this research.  ... 
doi:10.1186/s41239-019-0159-9 fatcat:7p6cs25ogzebjfxxei3hham33q

Individualizing Workplace Learning with Digital Technologies [chapter]

Antje Barabasch, Anna Keller
2021 Digital Transformation of Learning Organizations  
Overarching trends in terms of changing learning cultures in apprenticeship training, such as individualization, flexibilization, self-organized learning, project work or coaching, support the introduction  ...  Based on our findings, we will draw conclusions about how learning cultures are influencing the use of technologies and vice versa how the introduction of these technologies shapes innovative learning  ...  Apprentices, during their apprenticeship, are prepared to communicate, work and learn with digital technologies, for example using E-Learning and Web-Based Training in internal courses.  ... 
doi:10.1007/978-3-030-55878-9_7 fatcat:skzml2wu65e5bplwai7fpwb6eq
« Previous Showing results 1 — 15 out of 960 results