Add to ORKGA significant challenge in developing plan-ning 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 re-quires a huge number of plan traces to con-verge. In this paper, we show that the prob-lem with slow convergence can be circum-vented by having the learner generate solu-tion 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 cor-rect answers to a large percentage of planning problems in the test set. 1
Saving and reusing previously constructed plans is largely regarded as a promising approach to deal ...
Abstract. This paper describes a learning system for the auto-matic configuration of domain independ...
Abstract This paper introduces two new frameworks for learning action models for planning. In the mi...
A significant challenge in developing planning systems for practical applications is the difficulty ...
This paper introduces a framework for Planning while Learning where an agent is given a goal to achi...
Learningshows great promise to extend the generality and effectiveness of planning techniques. Resea...
This paper describes an explanation-based approach lo learning plans despite a computationally intra...
A great challenge in developing planning systems for practical applications is the difficulty of acq...
Abstract. Reinforcement learning (RL) involves sequential decision making in uncertain environments....
General-purpose generative planners use domain-independent search heuristics to generate solutions f...
Most of the available plan recognition techniques are based on the use of a plan library in order to...
Planning is the task of finding a set of operators whose executive transforms the current world stat...
We consider how to learn Hierarchical Task Networks (HTNs) for planning problems in which both the q...
In Automated planning, learning and exploiting additional knowledge within a domain model, in order ...
General-purpose generative planners use domain-independent search heuristics to generate solutions f...
Saving and reusing previously constructed plans is largely regarded as a promising approach to deal ...
Abstract. This paper describes a learning system for the auto-matic configuration of domain independ...
Abstract This paper introduces two new frameworks for learning action models for planning. In the mi...
A significant challenge in developing planning systems for practical applications is the difficulty ...
This paper introduces a framework for Planning while Learning where an agent is given a goal to achi...
Learningshows great promise to extend the generality and effectiveness of planning techniques. Resea...
This paper describes an explanation-based approach lo learning plans despite a computationally intra...
A great challenge in developing planning systems for practical applications is the difficulty of acq...
Abstract. Reinforcement learning (RL) involves sequential decision making in uncertain environments....
General-purpose generative planners use domain-independent search heuristics to generate solutions f...
Most of the available plan recognition techniques are based on the use of a plan library in order to...
Planning is the task of finding a set of operators whose executive transforms the current world stat...
We consider how to learn Hierarchical Task Networks (HTNs) for planning problems in which both the q...
In Automated planning, learning and exploiting additional knowledge within a domain model, in order ...
General-purpose generative planners use domain-independent search heuristics to generate solutions f...
Saving and reusing previously constructed plans is largely regarded as a promising approach to deal ...
Abstract. This paper describes a learning system for the auto-matic configuration of domain independ...
Abstract This paper introduces two new frameworks for learning action models for planning. In the mi...