Results 1  10
of
30
Learning domainspecific control knowledge from random walks
 In Proceedings of the fourteenth international
, 2004
"... We describe and evaluate a system for learning domainspecific control knowledge. In particular, given a planning domain, the goal is to output a control policy that performs well on “long random walk ” problem distributions. The system is based on viewing planning domains as very large Markov decisi ..."
Abstract

Cited by 32 (4 self)
 Add to MetaCart
We describe and evaluate a system for learning domainspecific control knowledge. In particular, given a planning domain, the goal is to output a control policy that performs well on “long random walk ” problem distributions. The system is based on viewing planning domains as very large Markov decision processes and then applying a recent variant of approximate policy iteration that is bootstrapped with a new technique based on random walks. We evaluate the system on the AIPS2000 planning domains (among others) and show that often the learned policies perform well on problems drawn from the long–randomwalk distribution. In addition, we show that these policies often perform well on the original problem distributions from the domains involved. Our evaluation also uncovers limitations of our current system that point to future challenges.
Learning Recursive Control Programs from Problem Solving
 JOURNAL OF MACHINE LEARNING RESEARCH
, 2006
"... In this paper, we propose a new representation for physical control  teleoreactive logic programs  along with an interpreter that uses them to achieve goals. In addition, we present a new learning method that acquires recursive forms of these structures from traces of successful problem solvin ..."
Abstract

Cited by 24 (10 self)
 Add to MetaCart
In this paper, we propose a new representation for physical control  teleoreactive logic programs  along with an interpreter that uses them to achieve goals. In addition, we present a new learning method that acquires recursive forms of these structures from traces of successful problem solving. We report
U.: HTNMAKER: Learning HTNs with minimal additional knowledge engineering required
 In: Proceedings of the TwentyThird Conference on Artificial Intelligence
, 2008
"... We describe HTNMAKER, an algorithm for learning hierarchical planning knowledge in the form of decomposition methods for Hierarchical Task Networks (HTNs). HTNMAKER takes as input the initial states from a set of classical planning problems in a planning domain and solutions to those problems, as ..."
Abstract

Cited by 21 (3 self)
 Add to MetaCart
We describe HTNMAKER, an algorithm for learning hierarchical planning knowledge in the form of decomposition methods for Hierarchical Task Networks (HTNs). HTNMAKER takes as input the initial states from a set of classical planning problems in a planning domain and solutions to those problems, as well as a set of semanticallyannotated tasks to be accomplished. The algorithm analyzes this semantic information in order to determine which portions of the input plans accomplish a particular task and constructs HTN methods based on those analyses. Our theoretical results show that HTNMAKER is sound and complete. We also present a formalism for a class of planning problems that are more expressive than classical planning. These planning problems can be represented as HTN planning problems. We show that the methods learned by HTNMAKER enable an HTN planner to solve those problems. Our experiments confirm the theoretical results and demonstrate convergence in three wellknown planning domains toward a set of HTN methods that can be used to solve nearly any problem expressible as a classical planning problem in that domain, relative to a set of goals.
MultiAgent Reinforcement Learning: Weighting and Partitioning
, 1999
"... This paper addresses weighting and partitioning in complex reinforcement learning tasks, with the aim of facilitating learning. The paper presents some ideas regarding weighting of multiple agents and extends them into partitioning an input/state space into multiple regions with differential weighti ..."
Abstract

Cited by 19 (11 self)
 Add to MetaCart
This paper addresses weighting and partitioning in complex reinforcement learning tasks, with the aim of facilitating learning. The paper presents some ideas regarding weighting of multiple agents and extends them into partitioning an input/state space into multiple regions with differential weighting in these regions, to exploit differential characteristics of regions and differential characteristics of agents to reduce the learning complexity of agents (and their function approximators) and thus to facilitate the learning overall. It analyzes, in reinforcement learning tasks, different ways of partitioning a task and using agents selectively based on partitioning. Based on the analysis, some heuristic methods are described and experimentally tested. We find that some offline heuristic methods performed the best, significantly better than singleagent models. Keywords: weighting, averaging, neural networks, partitioning, gating, reinforcement learning, 1 Introduction Multiple ag...
Learning teleoreactive logic programs from problem solving
 Proceedings of the Fifteenth International Conference on Inductive Logic Programming
, 2005
"... Abstract. In this paper, we focus on the problem of learning reactive skills for use by physical agents. We propose a new representation for such procedures, teleoreactive logic programs, along with an interpreter that utilizes them to achieve goals. After this, we describe a learning method that ac ..."
Abstract

Cited by 18 (7 self)
 Add to MetaCart
Abstract. In this paper, we focus on the problem of learning reactive skills for use by physical agents. We propose a new representation for such procedures, teleoreactive logic programs, along with an interpreter that utilizes them to achieve goals. After this, we describe a learning method that acquires these structures in a cumulative manner through problem solving. We report experiments in three domains that involve multiple levels of skilled behavior. We also review related work and discuss directions for future research. 1
Learning Horn Definitions with Equivalence and Membership Queries
 IN INTERNATIONAL WORKSHOP ON INDUCTIVE LOGIC PROGRAMMING
, 1997
"... A Horn definition is a set of Horn clauses with the same head literal. In this paper, we consider learning nonrecursive, functionfree firstorder Horn definitions. We show that this class is exactly learnable from equivalence and membership queries. It follows then that this class is PAC learnable ..."
Abstract

Cited by 15 (0 self)
 Add to MetaCart
A Horn definition is a set of Horn clauses with the same head literal. In this paper, we consider learning nonrecursive, functionfree firstorder Horn definitions. We show that this class is exactly learnable from equivalence and membership queries. It follows then that this class is PAC learnable using examples and membership queries. Our results have been shown to be applicable to learning efficient goaldecomposition rules in planning domains.
Learning Horn Definitions: Theory and an Application to Planning
 NEW GENERATION COMPUTING
, 1998
"... A Horn definition is a set of Horn clauses with the same head literal. In this paper, we consider learning nonrecursive, firstorder Horn definitions from entailment. We show that this class is exactly learnable from equivalence and membership queries. It follows then that this class is PAC learnab ..."
Abstract

Cited by 14 (5 self)
 Add to MetaCart
A Horn definition is a set of Horn clauses with the same head literal. In this paper, we consider learning nonrecursive, firstorder Horn definitions from entailment. We show that this class is exactly learnable from equivalence and membership queries. It follows then that this class is PAC learnable using examples and membership queries. Finally, we apply our results to learning control knowledge for efficient planning in the form of goaldecomposition rules.
Learning approximate preconditions for methods in hierarchical plans
 In Proceedings of the International Conference on Machine Learning (ICML
, 2005
"... A significant challenge in developing planning systems for practical applications is the difficulty of acquiring the domain knowledge needed by such systems. One method for acquiring this knowledge is to learn it from plan traces, but this method typically requires a huge number of plan traces to co ..."
Abstract

Cited by 11 (4 self)
 Add to MetaCart
A significant challenge in developing planning systems for practical applications is the difficulty of acquiring the domain knowledge needed by such systems. One method for acquiring this knowledge is to learn it from plan traces, but this method typically requires a huge number of plan traces to converge. In this paper, we show that the problem with slow convergence can be circumvented by having the learner generate solution plans even before the planning domain is completely learned. Our empirical results show that these improvements reduce the size of the training set that is needed to find correct answers to a large percentage of planning problems in the test set. 1.
Learning FirstOrder Acyclic Horn Programs from Entailment
 in Proceedings of the 15th International Conference on Machine Learning; (and Proceedings of the 8th International Conference on Inductive Logic Programming
, 1998
"... . In this paper, we consider learning firstorder Horn programs from entailment. In particular, we show that any subclass of firstorder acyclic Horn programs with constant arity is exactly learnable from equivalence and entailment membership queries provided it allows a polynomialtime subsumption ..."
Abstract

Cited by 11 (3 self)
 Add to MetaCart
. In this paper, we consider learning firstorder Horn programs from entailment. In particular, we show that any subclass of firstorder acyclic Horn programs with constant arity is exactly learnable from equivalence and entailment membership queries provided it allows a polynomialtime subsumption procedure and satisfies some closure conditions. One consequence of this is that firstorder acyclic determinate Horn programs with constant arity are exactly learnable from equivalence and entailment membership queries. 1 Introduction Learning firstorder Horn programssets of firstorder Horn clausesis an important problem in inductive logic programming with applications ranging from speedup learning to grammatical inference. We are interested in speedup learning, which concerns learning domainspecific control knowledge to alleviate the computational hardness of planning. One kind of control knowledge, which is particularly useful in many domains, is represented as goaldecomposition...
Learning preconditions for planning from plan traces and HTN structure
 Computational Intelligence
, 2005
"... Agreat challenge in developing planning systems for practical applications is the difficulty of acquiring the domain information needed to guide such systems. This paper describes a way to learn some of that knowledge. More specifically, the following points are discussed. (1) We introduce a theoret ..."
Abstract

Cited by 11 (3 self)
 Add to MetaCart
Agreat challenge in developing planning systems for practical applications is the difficulty of acquiring the domain information needed to guide such systems. This paper describes a way to learn some of that knowledge. More specifically, the following points are discussed. (1) We introduce a theoretical basis for formally defining algorithms that learn preconditions for Hierarchical Task Network (HTN) methods. (2) We describe Candidate Elimination Method Learner (CaMeL), a supervised, eager, and incremental learning process for preconditions of HTN methods. We state and prove theorems about CaMeL’s soundness, completeness, and convergence properties. (3) We present empirical results about CaMeL’s convergence under various conditions. Among other things, CaMeL converges the fastest on the preconditions of the HTN methods that are needed the most often. Thus CaMeL’s output can be useful even before it has fully converged.