Filters








193,637 Hits in 6.1 sec

Relational Reinforcement Learning [chapter]

M. D. Buhmann, Prem Melville, Vikas Sindhwani, Novi Quadrianto, Wray L. Buntine, Luís Torgo, Xinhua Zhang, Peter Stone, Jan Struyf, Hendrik Blockeel, Kurt Driessens, Risto Miikkulainen (+7 others)
2011 Encyclopedia of Machine Learning  
solve really hard problems.  ...  Adding guidance to the exploration phase of the RRL system, based on an available reasonable policy can greatly increase the performance of the RRL system in applications with sparse and hard to reach  ...  Conclusions This chapter addressed the problem of integrating guidance and experimentation in reinforcement learning, and in particular relational reinforcement learning as the problem of finding rewards  ... 
doi:10.1007/978-0-387-30164-8_721 fatcat:crivxryvsrcdjopevxwrtofrt4

Learning Relational Navigation Policies

Alexandru Cocora, Kristian Kersting, Christian Plagemann, Wolfram Burgard, Luc Raedt
2006 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems  
We propose to learn relational decision trees as abstract navigation strategies from example paths. Relational abstraction has several interesting and important properties.  ...  The majority of path planning approaches has been designed to entirely solve the given problem from scratch given the current and goal configurations of the robot.  ...  MDPs provide a sound theoretical framework to deal with uncertainty related to the robot's motor and perceptive actions during both planning and plan execution phases.  ... 
doi:10.1109/iros.2006.282061 dblp:conf/iros/CocoraKPBR06 fatcat:nhbtobmkunbybi6d4pcp7y66z4

Empirical Study of Relational Learning Algorithms in the Phase Transition Framework [chapter]

Erick Alphonse, Aomar Osmani
2009 Lecture Notes in Computer Science  
Relational Learning (RL) has aroused interest to fill the gap between efficient attribute-value learners and growing applications stored in multi-relational databases.  ...  As RL, in general, is Σ2 − hard, we propose a first random problem generator, which exhibits the phase transition of its decision version, beyond NP.  ...  Section 2 presents background information about relational learning and search strategies, as well as main results on the phase transition framework in combinatorics and the "easy-hard-easy" pattern.  ... 
doi:10.1007/978-3-642-04180-8_21 fatcat:mnylhzpnpnf3xlqidvpi27ca6a

Relational learning re-examined

Chris Thornton, Andy Clark
1997 Behavioral and Brain Sciences  
This commentary disputes this and suggests that recoding functions are adaptive specializations.  ...  Clark & Thornton argue that the recoding functions which are used to solve type-2 problems are, at least in part, the ontogenetic products of general-purpose mechanisms.  ...  Authors' Response Relational learning re-examined Abstract: We argue that existing learning algorithms are often poorly equipped to solve problems involving a certain type of important and widespread  ... 
doi:10.1017/s0140525x97440025 fatcat:jmhukn4z3ndvpkhjn2klaxtr6m

Phase transition and heuristic search in relational learning

Erick Alphonse, Aomar Osmani
2007 Sixth International Conference on Machine Learning and Applications (ICMLA 2007)  
Several works have shown that the covering test in relational learning exhibits a phase transition in its covering probability.  ...  We conclude that the location of the target concept with respect to the phase transition alone is not a reliable indication of the learning problem difficulty as previously thought.  ...  Conclusion Plateau phenomena in ILP have been studied recently in the phase transition framework and an important work has been done on identifying the criteria of success of learning algorithms [4] .  ... 
doi:10.1109/icmla.2007.102 dblp:conf/icmla/AlphonseO07 fatcat:kqt2aveudjb7nkqvzoftt2r6ve

Relational Reinforcement Learning [chapter]

Kurt Driessens
2001 Lecture Notes in Computer Science  
In particular, relational reinforcement learning allows us to employ structural representations, to abstract from specific goals pursued and to exploit the results of previous learning phases when addressing  ...  Within this simple domain we show that relational reinforcement learning solves some existing problems with reinforcement learning.  ...  The idea of experience replay is to memorize all experiences gathered so far and to repeatedly present them to the learning engines. The memorization of past experiences is similar to our work.  ... 
doi:10.1007/3-540-47745-4_12 fatcat:dmghtbtzm5aslmjcqhbif2ms6m

Relational reinforcement learning [chapter]

Sašo Džeroski, Luc De Raedt, Hendrik Blockeel
1998 Lecture Notes in Computer Science  
In particular, relational reinforcement learning allows us to employ structural representations, to abstract from specific goals pursued and to exploit the results of previous learning phases when addressing  ...  Within this simple domain we show that relational reinforcement learning solves some existing problems with reinforcement learning.  ...  The idea of experience replay is to memorize all experiences gathered so far and to repeatedly present them to the learning engines. The memorization of past experiences is similar to our work.  ... 
doi:10.1007/bfb0027307 fatcat:4rakivubvjcjdgao3cl5gtvb64

Relational Reinforcement Learning [chapter]

Kurt Driessens
2016 Encyclopedia of Machine Learning and Data Mining  
In particular, relational reinforcement learning allows us to employ structural representations, to abstract from specific goals pursued and to exploit the results of previous learning phases when addressing  ...  Within this simple domain we show that relational reinforcement learning solves some existing problems with reinforcement learning.  ...  The idea of experience replay is to memorize all experiences gathered so far and to repeatedly present them to the learning engines. The memorization of past experiences is similar to our work.  ... 
doi:10.1007/978-1-4899-7502-7_726-1 fatcat:nxodvv7wxjh73m7apy5nbiatai

Multi-agent Relational Reinforcement Learning [chapter]

Tom Croonenborghs, Karl Tuyls, Jan Ramon, Maurice Bruynooghe
2006 Lecture Notes in Computer Science  
Yet, this relational structure has not been exploited for multi-agent reinforcement learning tasks and has only been studied in a single agent context so far.  ...  More precisely, we consider an abstract multi-state coordination problem, which can be considered as a variation and extension of repeated stateless Dispersion Games.  ...  These characteristics make the transition from a one-agent system to a multi-agent system very hard.  ... 
doi:10.1007/11691839_12 fatcat:q6hfxggsinhjzk254b5crs3oxe

Machine learning of temporal relations

Inderjeet Mani, Marc Verhagen, Ben Wellner, Chong Min Lee, James Pustejovsky
2006 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06  
This paper investigates a machine learning approach for temporally ordering and anchoring events in natural language texts.  ...  Machine Learning Approach Initial Learner There are several sub-problems related to inferring event anchoring and event ordering.  ...  and anchoring problems.  ... 
doi:10.3115/1220175.1220270 dblp:conf/acl/ManiVWLP06 fatcat:yrxgxkcodbeork7ipp2dndesya

Relational Markov Networks [chapter]

2007 Introduction to Statistical Relational Learning  
We show how to train these models effectively, and how to use approximate probabilistic inference over the learned model for collective classification and link prediction.  ...  One of the key challenges for statistical relational learning is the design of a representation language that allows flexible modeling of complex relational interactions.  ...  Transitivity templates relate triples of objects and links organized in a triangle.  ... 
doi:10.7551/mitpress/7432.003.0008 fatcat:m2jh7lwrw5etbawboif4oe74pu

Feature Construction for Relational Sequence Learning [article]

Nicola Di Mauro and Teresa M.A. Basile and Stefano Ferilli and Floriana Esposito
2010 arXiv   pre-print
We tackle the problem of multi-class relational sequence learning using relevant patterns discovered from a set of labelled sequences.  ...  To deal with this problem, firstly each relational sequence is mapped into a feature vector using the result of a feature construction method.  ...  A way to tackle the task of learning discriminant functions in relational learning corresponds to reformulate the problem into an attribute-value form and then applying a propositional learner [4] .  ... 
arXiv:1006.5188v1 fatcat:xyifh2y4jfc7zcsfz2vog3nmjm

Learning to Relate Images

R. Memisevic
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper we review the recent work on relational feature learning, and we provide an analysis of the role that multiplicative interactions play in learning to encode relations.  ...  Recently, there has been an increasing interest in learning to infer correspondences from data using relational, spatio-temporal, and bi-linear variants of deep learning methods.  ...  Acknowledgements: This work was supported in part by the German Federal Ministry of Education and Research (BMBF) in the project 01GQ0841 (BFNT Frankfurt).  ... 
doi:10.1109/tpami.2013.53 pmid:23787339 fatcat:ehgjqhnlhnbv5ch7qm76uotvqy

Optimizing Probabilistic Models for Relational Sequence Learning [chapter]

Nicola Di Mauro, Teresa M. A. Basile, Stefano Ferilli, Floriana Esposito
2011 Lecture Notes in Computer Science  
This paper tackles the problem of relational sequence learning selecting relevant features elicited from a set of labelled sequences.  ...  The performance of the proposed method on a real-world dataset shows an improvement compared to other sequential statistical relational methods, such as Logical Hidden Markov Models and relational Conditional  ...  In this paper we propose an algorithm for relational sequence learning, named Lynx 1 , that works in two phases.  ... 
doi:10.1007/978-3-642-21916-0_27 fatcat:ooonnvoixbekflc5geb5lg6tri

Statistical relational learning for workflow mining

Elena Bellodi, Fabrizio Riguzzi, Evelina Lamma
2016 Intelligent Data Analysis  
We present a Statistical Relational Learning approach to Workflow Mining that takes into account both flexibility and uncertainty in real environments.  ...  One of the most interesting problems is the mining and representation of process models in a declarative language.  ...  checking" problem.  ... 
doi:10.3233/ida-160818 fatcat:mp3thyi5nfaj7nlcmtbunacn6m
« Previous Showing results 1 — 15 out of 193,637 results