Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288055502> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4288055502 abstract "Reinforcement learning (RL) has shown to reach super human-level performance across a wide range of tasks. However, unlike supervised machine learning, learning strategies that generalize well to a wide range of situations remains one of the most challenging problems for real-world RL. Autonomous driving (AD) provides a multi-faceted experimental field, as it is necessary to learn the correct behavior over many variations of road layouts and large distributions of possible traffic situations, including individual driver personalities and hard-to-predict traffic events. In this paper we propose a challenging benchmark for generalizable RL for AD based on a configurable, flexible, and performant code base. Our benchmark uses a catalog of randomized scenario generators, including multiple mechanisms for road layout and traffic variations, different numerical and visual observation types, distinct action spaces, diverse vehicle models, and allows for use under static scenario definitions. In addition to purely algorithmic insights, our application-oriented benchmark also enables a better understanding of the impact of design decisions such as action and observation space on the generalizability of policies. Our benchmark aims to encourage researchers to propose solutions that are able to successfully generalize across scenarios, a task in which current RL methods fail. The code for the benchmark is available at https://github.com/seawee1/driver-dojo." @default.
- W4288055502 created "2022-07-28" @default.
- W4288055502 creator A5005165731 @default.
- W4288055502 creator A5017751830 @default.
- W4288055502 creator A5023277657 @default.
- W4288055502 creator A5074880700 @default.
- W4288055502 creator A5075177955 @default.
- W4288055502 date "2022-07-23" @default.
- W4288055502 modified "2023-09-24" @default.
- W4288055502 title "Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving" @default.
- W4288055502 doi "https://doi.org/10.48550/arxiv.2207.11432" @default.
- W4288055502 hasPublicationYear "2022" @default.
- W4288055502 type Work @default.
- W4288055502 citedByCount "0" @default.
- W4288055502 crossrefType "posted-content" @default.
- W4288055502 hasAuthorship W4288055502A5005165731 @default.
- W4288055502 hasAuthorship W4288055502A5017751830 @default.
- W4288055502 hasAuthorship W4288055502A5023277657 @default.
- W4288055502 hasAuthorship W4288055502A5074880700 @default.
- W4288055502 hasAuthorship W4288055502A5075177955 @default.
- W4288055502 hasBestOaLocation W42880555021 @default.
- W4288055502 hasConcept C105795698 @default.
- W4288055502 hasConcept C119857082 @default.
- W4288055502 hasConcept C121332964 @default.
- W4288055502 hasConcept C127413603 @default.
- W4288055502 hasConcept C13280743 @default.
- W4288055502 hasConcept C146978453 @default.
- W4288055502 hasConcept C154945302 @default.
- W4288055502 hasConcept C177264268 @default.
- W4288055502 hasConcept C185798385 @default.
- W4288055502 hasConcept C199360897 @default.
- W4288055502 hasConcept C201995342 @default.
- W4288055502 hasConcept C204323151 @default.
- W4288055502 hasConcept C205649164 @default.
- W4288055502 hasConcept C27158222 @default.
- W4288055502 hasConcept C2776760102 @default.
- W4288055502 hasConcept C2780451532 @default.
- W4288055502 hasConcept C2780791683 @default.
- W4288055502 hasConcept C33923547 @default.
- W4288055502 hasConcept C41008148 @default.
- W4288055502 hasConcept C62520636 @default.
- W4288055502 hasConcept C97541855 @default.
- W4288055502 hasConceptScore W4288055502C105795698 @default.
- W4288055502 hasConceptScore W4288055502C119857082 @default.
- W4288055502 hasConceptScore W4288055502C121332964 @default.
- W4288055502 hasConceptScore W4288055502C127413603 @default.
- W4288055502 hasConceptScore W4288055502C13280743 @default.
- W4288055502 hasConceptScore W4288055502C146978453 @default.
- W4288055502 hasConceptScore W4288055502C154945302 @default.
- W4288055502 hasConceptScore W4288055502C177264268 @default.
- W4288055502 hasConceptScore W4288055502C185798385 @default.
- W4288055502 hasConceptScore W4288055502C199360897 @default.
- W4288055502 hasConceptScore W4288055502C201995342 @default.
- W4288055502 hasConceptScore W4288055502C204323151 @default.
- W4288055502 hasConceptScore W4288055502C205649164 @default.
- W4288055502 hasConceptScore W4288055502C27158222 @default.
- W4288055502 hasConceptScore W4288055502C2776760102 @default.
- W4288055502 hasConceptScore W4288055502C2780451532 @default.
- W4288055502 hasConceptScore W4288055502C2780791683 @default.
- W4288055502 hasConceptScore W4288055502C33923547 @default.
- W4288055502 hasConceptScore W4288055502C41008148 @default.
- W4288055502 hasConceptScore W4288055502C62520636 @default.
- W4288055502 hasConceptScore W4288055502C97541855 @default.
- W4288055502 hasLocation W42880555021 @default.
- W4288055502 hasOpenAccess W4288055502 @default.
- W4288055502 hasPrimaryLocation W42880555021 @default.
- W4288055502 hasRelatedWork W102453 @default.
- W4288055502 hasRelatedWork W11122729 @default.
- W4288055502 hasRelatedWork W12594185 @default.
- W4288055502 hasRelatedWork W2683128 @default.
- W4288055502 hasRelatedWork W3942861 @default.
- W4288055502 hasRelatedWork W5547603 @default.
- W4288055502 hasRelatedWork W5991403 @default.
- W4288055502 hasRelatedWork W868042 @default.
- W4288055502 hasRelatedWork W8801238 @default.
- W4288055502 hasRelatedWork W9761094 @default.
- W4288055502 isParatext "false" @default.
- W4288055502 isRetracted "false" @default.
- W4288055502 workType "article" @default.