Home > Search Results: Komenda, Antonín
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 2 records found  Search took 0.01 seconds. 
Heuristic Learning for Domain-independent Planning
 Trunda, Otakar ; Barták, Roman (advisor) ; Onaindia, Eva (referee) ; Komenda, Antonín (referee)
Automated planning deals with the problem of finding a sequence of actions leading from a given state to a desired state, e.g., solving Rubik's Cube, delivering parcels, etc. The state-of-the-art automated planning techniques exploit informed forward search guided by a heuristic, where the heuristic estimates a distance from a state to a goal state. In this thesis, we present a technique to automatically construct an efficient heuristic for a given planning domain. The proposed approach is based on training a deep neural network using a set of previously solved planning problems from the same domain. We use a novel way of extracting features for states which doesn't depend on usage of existing heuristics. The trained network can be used as a heuristic on any problem from the domain of interest without any limitation on the problem size. Our experiments show that the technique is competitive with popular domain-independent heuristic. We also introduce a theoretical framework to formally analyze behavior of learned heuristics. We state and prove several theorems that establish bounds on the worst-case performance of learned heuristics.
Detailed record
Tools for virtual agent behavior specification in POSH
 Havlíček, Jan ; Gemrot, Jakub (advisor) ; Komenda, Antonín (referee)
Goal of the work is to improve the SPOSH planner and its developement tools. SPOSH is a reactive planner of virtual agents similar to behavior trees that is used in the Pogamut platform, which is used to develop virtual agents. SPOSH itself suffers from several problems, especially excessive duplication of primitives (actions and senses) in different agents and unnatural execution of primitives. This work aims to remove these problems. Nearly all behavior tree planners are not public and developement tools are not usually available. Absence of such tools, especially of debugger, is major problem for users. Part of this work are tools for easy creation and debugging of SPOSH plans. Improved planner and created tools are demonstrated using an agent in game Unreal Tournament 2004.
Detailed record

See also: similar author names
2 Komenda, Adam
Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English