Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382319487> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4382319487 abstract "Abstract Autonomous robots can be employed in exploring unknown environments and performing many tasks, such as, e.g. detecting areas of interest, collecting target objects, etc. Deep reinforcement learning (RL) is often used to train this kind of robot. However, concerning the artificial environments aimed at testing the robot, there is a lack of available data sets and a long time is needed to create them from scratch. A good data set is in fact usually produced with high effort in terms of cost and human work to satisfy the constraints imposed by the expected results. In the first part of this paper, we focus on the specification of the properties of the solutions needed to build a data set, making the case of environment exploration. In the proposed approach, rather than using imperative programming, we explore the possibility of generating data sets using constraint programming in Prolog. In this phase, geometric predicates describe a virtual environment according to inter-space requirements. The second part of the paper is focused on testing the generated data set in an AI gym via space search techniques. We developed a Neuro-Symbolic agent built from the following: (i) A deep Q-learning component implemented in Python, able to address via RL a search problem in the virtual space; the agent has the goal to explore a generated virtual environment to seek for a target, improving its performance through a RL process. (ii) A symbolic component able to re-address the search when the Q-learning component gets stuck in a part of the virtual environment; these components stimulate the agent to move to and explore other parts of the environment. Wide experimentation has been performed, with promising results, and is reported, to demonstrate the effectiveness of the approach." @default.
- W4382319487 created "2023-06-28" @default.
- W4382319487 creator A5012714475 @default.
- W4382319487 creator A5014004028 @default.
- W4382319487 creator A5021862093 @default.
- W4382319487 creator A5023765348 @default.
- W4382319487 creator A5058247188 @default.
- W4382319487 creator A5092123219 @default.
- W4382319487 date "2023-06-07" @default.
- W4382319487 modified "2023-09-28" @default.
- W4382319487 title "Extension of constraint-procedural logic-generated environments for deep Q-learning agent training and benchmarking" @default.
- W4382319487 cites W1549847324 @default.
- W4382319487 cites W1608309740 @default.
- W4382319487 cites W2060020482 @default.
- W4382319487 cites W2060498389 @default.
- W4382319487 cites W2084202433 @default.
- W4382319487 cites W2152660354 @default.
- W4382319487 cites W2397253692 @default.
- W4382319487 cites W2534314849 @default.
- W4382319487 cites W2540236031 @default.
- W4382319487 cites W2746553466 @default.
- W4382319487 cites W2893641169 @default.
- W4382319487 cites W3111135479 @default.
- W4382319487 cites W32403112 @default.
- W4382319487 cites W4233642774 @default.
- W4382319487 doi "https://doi.org/10.1093/logcom/exad032" @default.
- W4382319487 hasPublicationYear "2023" @default.
- W4382319487 type Work @default.
- W4382319487 citedByCount "0" @default.
- W4382319487 crossrefType "journal-article" @default.
- W4382319487 hasAuthorship W4382319487A5012714475 @default.
- W4382319487 hasAuthorship W4382319487A5014004028 @default.
- W4382319487 hasAuthorship W4382319487A5021862093 @default.
- W4382319487 hasAuthorship W4382319487A5023765348 @default.
- W4382319487 hasAuthorship W4382319487A5058247188 @default.
- W4382319487 hasAuthorship W4382319487A5092123219 @default.
- W4382319487 hasConcept C105795698 @default.
- W4382319487 hasConcept C119857082 @default.
- W4382319487 hasConcept C121332964 @default.
- W4382319487 hasConcept C137631369 @default.
- W4382319487 hasConcept C154945302 @default.
- W4382319487 hasConcept C168167062 @default.
- W4382319487 hasConcept C173404611 @default.
- W4382319487 hasConcept C177264268 @default.
- W4382319487 hasConcept C199360897 @default.
- W4382319487 hasConcept C33923547 @default.
- W4382319487 hasConcept C41008148 @default.
- W4382319487 hasConcept C519991488 @default.
- W4382319487 hasConcept C80444323 @default.
- W4382319487 hasConcept C81721847 @default.
- W4382319487 hasConcept C90509273 @default.
- W4382319487 hasConcept C97355855 @default.
- W4382319487 hasConcept C97541855 @default.
- W4382319487 hasConceptScore W4382319487C105795698 @default.
- W4382319487 hasConceptScore W4382319487C119857082 @default.
- W4382319487 hasConceptScore W4382319487C121332964 @default.
- W4382319487 hasConceptScore W4382319487C137631369 @default.
- W4382319487 hasConceptScore W4382319487C154945302 @default.
- W4382319487 hasConceptScore W4382319487C168167062 @default.
- W4382319487 hasConceptScore W4382319487C173404611 @default.
- W4382319487 hasConceptScore W4382319487C177264268 @default.
- W4382319487 hasConceptScore W4382319487C199360897 @default.
- W4382319487 hasConceptScore W4382319487C33923547 @default.
- W4382319487 hasConceptScore W4382319487C41008148 @default.
- W4382319487 hasConceptScore W4382319487C519991488 @default.
- W4382319487 hasConceptScore W4382319487C80444323 @default.
- W4382319487 hasConceptScore W4382319487C81721847 @default.
- W4382319487 hasConceptScore W4382319487C90509273 @default.
- W4382319487 hasConceptScore W4382319487C97355855 @default.
- W4382319487 hasConceptScore W4382319487C97541855 @default.
- W4382319487 hasLocation W43823194871 @default.
- W4382319487 hasOpenAccess W4382319487 @default.
- W4382319487 hasPrimaryLocation W43823194871 @default.
- W4382319487 hasRelatedWork W1596719193 @default.
- W4382319487 hasRelatedWork W1600568876 @default.
- W4382319487 hasRelatedWork W1964013298 @default.
- W4382319487 hasRelatedWork W1996683955 @default.
- W4382319487 hasRelatedWork W2112962394 @default.
- W4382319487 hasRelatedWork W4210498713 @default.
- W4382319487 hasRelatedWork W4319083788 @default.
- W4382319487 hasRelatedWork W4380901377 @default.
- W4382319487 hasRelatedWork W67092138 @default.
- W4382319487 hasRelatedWork W2473250120 @default.
- W4382319487 isParatext "false" @default.
- W4382319487 isRetracted "false" @default.
- W4382319487 workType "article" @default.