Applying probabilistic rules to relational worlds

Being able to represent and reason about the world as though it were composed of "objects" seems like a useful abstraction. The typical approach to representing a world composed of objects is to use a relational representation; however, other representations, such as deictic representations, have also been studied. I am interested not only in an agent that is able to represent objects, but in one that is also able to act in order to achieve some task. This requires the ability to learn a plan of action. While value-based approaches to learning plans have been studied in the past, both with relational and deictic representations, I believe the shortcomings uncovered by those studies can be overcome by the use of a world model. Knowledge about how the world works has the advantage of being re-usable across specific tasks. In general, however, it is difficult to obtain a completely specified model about the world. This work attempts to characterize an approach to planning in a relational domain when the world model is represented as a potentially incomplete and/or redundant set of uncertain rules. Thesis Supervisor: Leslie Pack Kaelbling Title: Professor of Electrical Engineering and Computer Science

[1]  David Chapman,et al.  Pengi: An Implementation of a Theory of Activity , 1987, AAAI.

[2]  Luc De Raedt,et al.  Bayesian Logic Programs , 2001, ILP Work-in-progress reports.

[3]  Thomas Lukasiewicz,et al.  Probabilistic logic programming with conditional constraints , 2001, TOCL.

[4]  Yishay Mansour,et al.  A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes , 1999, Machine Learning.

[5]  Luc De Raedt,et al.  Clausal Discovery , 1997, Machine Learning.

[6]  Avi Pfeffer,et al.  Learning Probabilities for Noisy First-Order Rules , 1997, IJCAI.

[7]  Nils J. Nilsson,et al.  Probabilistic Logic * , 2022 .

[8]  Roni Khardon,et al.  Learning Action Strategies for Planning Domains , 1999, Artif. Intell..

[9]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[10]  Natalia H. Gardiol,et al.  Learning with Deictic Representation , 2002 .

[11]  Richard S. Sutton,et al.  Predictive Representations of State , 2001, NIPS.

[12]  Daniel Hunter,et al.  Causality and maximum entropy updating , 1989, Int. J. Approx. Reason..

[13]  Wei-Min Shen.  Discovery as autonomous learning from the environment , 2004, Machine Learning.

[14]  Ronald J. Brachman,et al.  An overview of the KL-ONE Knowledge Representation System , 1985 .

[15]  Manfred Jaeger,et al.  Relational Bayesian Networks , 1997, UAI.

[16]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[17]  Joseph Y. Halpern.  An Analysis of First-Order Logics of Probability , 1989, IJCAI.

[18]  Andrew McCallum,et al.  Reinforcement learning with selective perception and hidden state , 1996 .

[19]  Stuart J. Russell,et al.  Approximate inference for first-order probabilistic languages , 2001, IJCAI.

[20]  Philip E. Agre,et al.  The dynamic structure of everyday life , 1988 .

[21]  Tim Oates,et al.  The Thing that we Tried Didn't Work very Well: Deictic Representation in Reinforcement Learning , 2002, UAI.

[22]  L. Kaelbling,et al.  Learning with Deictic Representations , 2001 .

[23]  Keiji Kanazawa,et al.  A model for reasoning about persistence and causation , 1989 .

[24]  Luc De Raedt,et al.  Relational Reinforcement Learning , 2001, Machine Learning.

[25]  Robert Givan,et al.  Taxonomic syntax for first order inference , 1989, JACM.

[26]  Peter Haddawy,et al.  Answering Queries from Context-Sensitive Probabilistic Knowledge Bases (cid:3) , 1996 .

[27]  Andrew McCallum,et al.  Instance-Based Utile Distinctions for Reinforcement Learning with Hidden State , 1995, ICML.

[28]  Fahiem Bacchus,et al.  Using temporal logics to express search control knowledge for planning , 2000, Artif. Intell..

[29]  Leslie Pack Kaelbling,et al.  Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons , 1991, IJCAI.

[30]  Joseph Y. Halpern,et al.  From Statistical Knowledge Bases to Degrees of Belief , 1996, Artif. Intell..

[31]  Thomas Lukasiewicz,et al.  Probalilistic Logic Programming under Maximum Entropy , 1999, ESCQARU.

[32]  Eric B. Baum,et al.  Toward a Model of Mind as a Laissez-Faire Economy of Idiots , 1996, ICML.

[33]  Luc De Raedt,et al.  Using Logical Decision Trees for Clustering , 1997, ILP.

[34]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[35]  Avi Pfeffer,et al.  Probabilistic Frame-Based Systems , 1998, AAAI/IAAI.

[36]  Raymond Reiter,et al.  Knowledge in Action: Logical Foundations for Specifying and Implementing Dynamical Systems , 2001 .

[37]  Bernhard Nebel,et al.  Computational Complexity of Terminological Reasoning in BACK , 1988, Artif. Intell..

[38]  Luc De Raedt,et al.  DLAB: A Declarative Language Bias Formalism , 1996, ISMIS.

[39]  Craig Boutilier,et al.  Symbolic Dynamic Programming for First-Order MDPs , 2001, IJCAI.

[40]  Gary L. Drescher,et al.  Made-up minds - a constructivist approach to artificial intelligence , 1991 .

[41]  Kurt Driessens,et al.  Speeding Up Relational Reinforcement Learning through the Use of an Incremental First Order Decision Tree Learner , 2001, ECML.

[42]  Lise Getoor,et al.  Learning Probabilistic Relational Models , 1999, IJCAI.

[43]  Hans Reichenbach,et al.  The theory of probability , 1968 .

[44]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[45]  H. Jeffreys,et al.  The Theory of Probability , 1896 .

[46]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[47]  Robert Givan,et al.  Inductive Policy Selection for First-Order MDPs , 2002, UAI.

[48]  R. Rivest.  Learning Decision Lists , 1987, Machine Learning.

[49]  Hector J. Levesque,et al.  The Tractability of Subsumption in Frame-Based Description Languages , 1984, AAAI.

[50]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[51]  Hector Geffner,et al.  Learning Generalized Policies in Planning Using Concept Languages , 2000, KR.

[52]  Alex M. Andrew,et al.  Reinforcement Learning: : An Introduction , 1998 .

[53]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .