Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118172322> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3118172322 abstract "This paper investigates how a Bayesian reinforcement learning method can be used to create a tactical decision-making agent for autonomous driving in an intersection scenario, where the agent can estimate the confidence of its decisions. An ensemble of neural networks, with additional randomized prior functions (RPF), are trained by using a bootstrapped experience replay memory. The coefficient of variation in the estimated Q-values of the ensemble members is used to approximate the uncertainty, and a criterion that determines if the agent is sufficiently confident to make a particular decision is introduced. The performance of the ensemble RPF method is evaluated in an intersection scenario and compared to a standard Deep Q-Network method, which does not estimate the uncertainty. It is shown that the trained ensemble RPF agent can detect cases with high uncertainty, both in situations that are far from the training distribution, and in situations that seldom occur within the training distribution. This work demonstrates one possible application of such a confidence estimate, by using this information to choose safe actions in unknown situations, which removes all collisions from within the training distribution, and most collisions outside of the distribution." @default.
- W3118172322 created "2021-01-05" @default.
- W3118172322 creator A5016897258 @default.
- W3118172322 creator A5017046593 @default.
- W3118172322 creator A5079076790 @default.
- W3118172322 date "2020-09-20" @default.
- W3118172322 modified "2023-10-11" @default.
- W3118172322 title "Reinforcement Learning with Uncertainty Estimation for Tactical Decision-Making in Intersections" @default.
- W3118172322 cites W1965455100 @default.
- W3118172322 cites W2103328396 @default.
- W3118172322 cites W2124181495 @default.
- W3118172322 cites W2145339207 @default.
- W3118172322 cites W2168359464 @default.
- W3118172322 cites W2488452937 @default.
- W3118172322 cites W2905173465 @default.
- W3118172322 cites W2962977206 @default.
- W3118172322 cites W2963322416 @default.
- W3118172322 cites W2963625099 @default.
- W3118172322 cites W2989730386 @default.
- W3118172322 cites W2989958156 @default.
- W3118172322 cites W3102777717 @default.
- W3118172322 cites W3148740559 @default.
- W3118172322 cites W32403112 @default.
- W3118172322 cites W4241644338 @default.
- W3118172322 doi "https://doi.org/10.1109/itsc45102.2020.9294407" @default.
- W3118172322 hasPublicationYear "2020" @default.
- W3118172322 type Work @default.
- W3118172322 sameAs 3118172322 @default.
- W3118172322 citedByCount "14" @default.
- W3118172322 countsByYear W31181723222021 @default.
- W3118172322 countsByYear W31181723222022 @default.
- W3118172322 countsByYear W31181723222023 @default.
- W3118172322 crossrefType "proceedings-article" @default.
- W3118172322 hasAuthorship W3118172322A5016897258 @default.
- W3118172322 hasAuthorship W3118172322A5017046593 @default.
- W3118172322 hasAuthorship W3118172322A5079076790 @default.
- W3118172322 hasBestOaLocation W31181723222 @default.
- W3118172322 hasConcept C107673813 @default.
- W3118172322 hasConcept C119857082 @default.
- W3118172322 hasConcept C127413603 @default.
- W3118172322 hasConcept C146978453 @default.
- W3118172322 hasConcept C154945302 @default.
- W3118172322 hasConcept C33724603 @default.
- W3118172322 hasConcept C41008148 @default.
- W3118172322 hasConcept C50644808 @default.
- W3118172322 hasConcept C64543145 @default.
- W3118172322 hasConcept C97541855 @default.
- W3118172322 hasConceptScore W3118172322C107673813 @default.
- W3118172322 hasConceptScore W3118172322C119857082 @default.
- W3118172322 hasConceptScore W3118172322C127413603 @default.
- W3118172322 hasConceptScore W3118172322C146978453 @default.
- W3118172322 hasConceptScore W3118172322C154945302 @default.
- W3118172322 hasConceptScore W3118172322C33724603 @default.
- W3118172322 hasConceptScore W3118172322C41008148 @default.
- W3118172322 hasConceptScore W3118172322C50644808 @default.
- W3118172322 hasConceptScore W3118172322C64543145 @default.
- W3118172322 hasConceptScore W3118172322C97541855 @default.
- W3118172322 hasFunder F4320321030 @default.
- W3118172322 hasLocation W31181723221 @default.
- W3118172322 hasLocation W31181723222 @default.
- W3118172322 hasOpenAccess W3118172322 @default.
- W3118172322 hasPrimaryLocation W31181723221 @default.
- W3118172322 hasRelatedWork W2959276766 @default.
- W3118172322 hasRelatedWork W2961085424 @default.
- W3118172322 hasRelatedWork W3005880661 @default.
- W3118172322 hasRelatedWork W3049333768 @default.
- W3118172322 hasRelatedWork W3074294383 @default.
- W3118172322 hasRelatedWork W3212758104 @default.
- W3118172322 hasRelatedWork W4206669594 @default.
- W3118172322 hasRelatedWork W4295941380 @default.
- W3118172322 hasRelatedWork W4319083788 @default.
- W3118172322 hasRelatedWork W4385957992 @default.
- W3118172322 isParatext "false" @default.
- W3118172322 isRetracted "false" @default.
- W3118172322 magId "3118172322" @default.
- W3118172322 workType "article" @default.