FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328007630> ?p ?o ?g. }

• W4328007630 endingPage "28550" @default.
• W4328007630 startingPage "28522" @default.
• W4328007630 abstract "As deep learning models have become increasingly complex, it is critical to understand their decision-making, particularly in safety-relevant applications. In order to support a quantitative interpretation of an autonomous agent trained through Deep Reinforcement Learning (DRL) in the highway-env simulation environment, we propose a framework featuring three types of views for analyzing data: (i) episode timeline, (ii) frame by frame, and (iii) aggregated statistical analysis, also including heatmaps for a better spatial understanding. Our methodology allowed a novel, consistent description of the behavior of the agent. The main motivator for the taken action is typically the longitudinal distance from the second-closest and, to a lower extent, third-closest vehicle. In the overtakes, also the agent’s position in lanes becomes relevant. The analysis identified interesting patterns and an issue in the last frames of an episode, when the agent is unable to overtake the last two vehicles, arguably because of the lack of reference vehicles ahead. We observed a clear differentiation between attention and SHAP values (estimating the importance of each feature for each decision), reflecting the architecture of the neural network, where the first layer implements the attention mechanism, while the deeper ones make the actual decision. Attention focuses on the proximity of the ego, while the decision is taken on a wider horizon, denoting a valuable anticipation capability. To support research, the proposed framework is released as open source." @default.
• W4328007630 created "2023-03-22" @default.
• W4328007630 creator A5011105820 @default.
• W4328007630 creator A5034705217 @default.
• W4328007630 creator A5056890512 @default.
• W4328007630 creator A5082344846 @default.
• W4328007630 creator A5086805863 @default.
• W4328007630 creator A5087911127 @default.
• W4328007630 date "2023-01-01" @default.
• W4328007630 modified "2023-10-05" @default.
• W4328007630 title "Explaining a Deep Reinforcement Learning (DRL)-Based Automated Driving Agent in Highway Simulations" @default.
• W4328007630 cites W1965455100 @default.
• W4328007630 cites W1991665457 @default.
• W4328007630 cites W1997619170 @default.
• W4328007630 cites W2055501135 @default.
• W4328007630 cites W2095095223 @default.
• W4328007630 cites W2096192437 @default.
• W4328007630 cites W2125223451 @default.
• W4328007630 cites W2145339207 @default.
• W4328007630 cites W2167052694 @default.
• W4328007630 cites W2282821441 @default.
• W4328007630 cites W2336525064 @default.
• W4328007630 cites W2616635592 @default.
• W4328007630 cites W2657631929 @default.
• W4328007630 cites W2741086815 @default.
• W4328007630 cites W2766836212 @default.
• W4328007630 cites W2769282630 @default.
• W4328007630 cites W2903709398 @default.
• W4328007630 cites W2911964244 @default.
• W4328007630 cites W2945295328 @default.
• W4328007630 cites W2945976633 @default.
• W4328007630 cites W2946231253 @default.
• W4328007630 cites W2950768109 @default.
• W4328007630 cites W2953920792 @default.
• W4328007630 cites W2956161617 @default.
• W4328007630 cites W2962687116 @default.
• W4328007630 cites W2962772482 @default.
• W4328007630 cites W3016826426 @default.
• W4328007630 cites W3034837210 @default.
• W4328007630 cites W3086911381 @default.
• W4328007630 cites W3100366369 @default.
• W4328007630 cites W3116286104 @default.
• W4328007630 cites W3126775045 @default.
• W4328007630 cites W3146366485 @default.
• W4328007630 cites W3194357095 @default.
• W4328007630 cites W3198156002 @default.
• W4328007630 cites W3202283237 @default.
• W4328007630 cites W3209901185 @default.
• W4328007630 cites W3210631399 @default.
• W4328007630 cites W3210800887 @default.
• W4328007630 cites W3212357731 @default.
• W4328007630 cites W32403112 @default.
• W4328007630 cites W4205128884 @default.
• W4328007630 cites W4205272462 @default.
• W4328007630 cites W4210361514 @default.
• W4328007630 doi "https://doi.org/10.1109/access.2023.3259544" @default.
• W4328007630 hasPublicationYear "2023" @default.
• W4328007630 type Work @default.
• W4328007630 citedByCount "0" @default.
• W4328007630 crossrefType "journal-article" @default.
• W4328007630 hasAuthorship W4328007630A5011105820 @default.
• W4328007630 hasAuthorship W4328007630A5034705217 @default.
• W4328007630 hasAuthorship W4328007630A5056890512 @default.
• W4328007630 hasAuthorship W4328007630A5082344846 @default.
• W4328007630 hasAuthorship W4328007630A5086805863 @default.
• W4328007630 hasAuthorship W4328007630A5087911127 @default.
• W4328007630 hasBestOaLocation W43280076301 @default.
• W4328007630 hasConcept C107457646 @default.
• W4328007630 hasConcept C119857082 @default.
• W4328007630 hasConcept C126042441 @default.
• W4328007630 hasConcept C138885662 @default.
• W4328007630 hasConcept C154945302 @default.
• W4328007630 hasConcept C166957645 @default.
• W4328007630 hasConcept C176777502 @default.
• W4328007630 hasConcept C2776401178 @default.
• W4328007630 hasConcept C41008148 @default.
• W4328007630 hasConcept C41895202 @default.
• W4328007630 hasConcept C4438859 @default.
• W4328007630 hasConcept C76155785 @default.
• W4328007630 hasConcept C95457728 @default.
• W4328007630 hasConcept C97541855 @default.
• W4328007630 hasConceptScore W4328007630C107457646 @default.
• W4328007630 hasConceptScore W4328007630C119857082 @default.
• W4328007630 hasConceptScore W4328007630C126042441 @default.
• W4328007630 hasConceptScore W4328007630C138885662 @default.
• W4328007630 hasConceptScore W4328007630C154945302 @default.
• W4328007630 hasConceptScore W4328007630C166957645 @default.
• W4328007630 hasConceptScore W4328007630C176777502 @default.
• W4328007630 hasConceptScore W4328007630C2776401178 @default.
• W4328007630 hasConceptScore W4328007630C41008148 @default.
• W4328007630 hasConceptScore W4328007630C41895202 @default.
• W4328007630 hasConceptScore W4328007630C4438859 @default.
• W4328007630 hasConceptScore W4328007630C76155785 @default.
• W4328007630 hasConceptScore W4328007630C95457728 @default.
• W4328007630 hasConceptScore W4328007630C97541855 @default.
• W4328007630 hasLocation W43280076301 @default.
• W4328007630 hasOpenAccess W4328007630 @default.
• W4328007630 hasPrimaryLocation W43280076301 @default.

• next