Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200659275> ?p ?o ?g. }
- W3200659275 abstract "We present the single track road problem. In this problem two agents face each-other at opposite positions of a road that can only have one agent pass at a time. We focus on the scenario in which one agent is human, while the other is an autonomous agent. We run experiments with human subjects in a simple grid domain, which simulates the single track road problem. We show that when data is limited, building an accurate human model is very challenging, and that a reinforcement learning agent, which is based on this data, does not perform well in practice. However, we show that an agent that tries to maximize a linear combination of the human's utility and its own utility, achieves a high score, and significantly outperforms other baselines, including an agent that tries to maximize only its own utility." @default.
- W3200659275 created "2021-09-27" @default.
- W3200659275 creator A5077377835 @default.
- W3200659275 creator A5082567694 @default.
- W3200659275 date "2021-09-12" @default.
- W3200659275 modified "2023-09-26" @default.
- W3200659275 title "A Socially Aware Reinforcement Learning Agent for The Single Track Road Problem" @default.
- W3200659275 cites W1713503745 @default.
- W3200659275 cites W1952987468 @default.
- W3200659275 cites W2044944116 @default.
- W3200659275 cites W2045350176 @default.
- W3200659275 cites W2055556996 @default.
- W3200659275 cites W2061562262 @default.
- W3200659275 cites W2061826561 @default.
- W3200659275 cites W2085252383 @default.
- W3200659275 cites W2087577266 @default.
- W3200659275 cites W2096452841 @default.
- W3200659275 cites W2112794329 @default.
- W3200659275 cites W2121863487 @default.
- W3200659275 cites W2141309697 @default.
- W3200659275 cites W2155014708 @default.
- W3200659275 cites W2215417395 @default.
- W3200659275 cites W2223395375 @default.
- W3200659275 cites W2292550996 @default.
- W3200659275 cites W2327678559 @default.
- W3200659275 cites W2395149932 @default.
- W3200659275 cites W2519467189 @default.
- W3200659275 cites W2608536805 @default.
- W3200659275 cites W2745547123 @default.
- W3200659275 cites W2796018000 @default.
- W3200659275 cites W2918814536 @default.
- W3200659275 cites W2963906196 @default.
- W3200659275 cites W3037376004 @default.
- W3200659275 cites W3122078363 @default.
- W3200659275 cites W3136121014 @default.
- W3200659275 cites W3141392623 @default.
- W3200659275 cites W378366556 @default.
- W3200659275 doi "https://doi.org/10.48550/arxiv.2109.05486" @default.
- W3200659275 hasPublicationYear "2021" @default.
- W3200659275 type Work @default.
- W3200659275 sameAs 3200659275 @default.
- W3200659275 citedByCount "0" @default.
- W3200659275 crossrefType "posted-content" @default.
- W3200659275 hasAuthorship W3200659275A5077377835 @default.
- W3200659275 hasAuthorship W3200659275A5082567694 @default.
- W3200659275 hasBestOaLocation W32006592751 @default.
- W3200659275 hasConcept C111472728 @default.
- W3200659275 hasConcept C111919701 @default.
- W3200659275 hasConcept C119857082 @default.
- W3200659275 hasConcept C120665830 @default.
- W3200659275 hasConcept C121332964 @default.
- W3200659275 hasConcept C134306372 @default.
- W3200659275 hasConcept C138885662 @default.
- W3200659275 hasConcept C144024400 @default.
- W3200659275 hasConcept C154945302 @default.
- W3200659275 hasConcept C187691185 @default.
- W3200659275 hasConcept C192209626 @default.
- W3200659275 hasConcept C2524010 @default.
- W3200659275 hasConcept C2779304628 @default.
- W3200659275 hasConcept C2780586882 @default.
- W3200659275 hasConcept C33923547 @default.
- W3200659275 hasConcept C36289849 @default.
- W3200659275 hasConcept C36503486 @default.
- W3200659275 hasConcept C41008148 @default.
- W3200659275 hasConcept C89992363 @default.
- W3200659275 hasConcept C97541855 @default.
- W3200659275 hasConceptScore W3200659275C111472728 @default.
- W3200659275 hasConceptScore W3200659275C111919701 @default.
- W3200659275 hasConceptScore W3200659275C119857082 @default.
- W3200659275 hasConceptScore W3200659275C120665830 @default.
- W3200659275 hasConceptScore W3200659275C121332964 @default.
- W3200659275 hasConceptScore W3200659275C134306372 @default.
- W3200659275 hasConceptScore W3200659275C138885662 @default.
- W3200659275 hasConceptScore W3200659275C144024400 @default.
- W3200659275 hasConceptScore W3200659275C154945302 @default.
- W3200659275 hasConceptScore W3200659275C187691185 @default.
- W3200659275 hasConceptScore W3200659275C192209626 @default.
- W3200659275 hasConceptScore W3200659275C2524010 @default.
- W3200659275 hasConceptScore W3200659275C2779304628 @default.
- W3200659275 hasConceptScore W3200659275C2780586882 @default.
- W3200659275 hasConceptScore W3200659275C33923547 @default.
- W3200659275 hasConceptScore W3200659275C36289849 @default.
- W3200659275 hasConceptScore W3200659275C36503486 @default.
- W3200659275 hasConceptScore W3200659275C41008148 @default.
- W3200659275 hasConceptScore W3200659275C89992363 @default.
- W3200659275 hasConceptScore W3200659275C97541855 @default.
- W3200659275 hasLocation W32006592751 @default.
- W3200659275 hasOpenAccess W3200659275 @default.
- W3200659275 hasPrimaryLocation W32006592751 @default.
- W3200659275 hasRelatedWork W2923653485 @default.
- W3200659275 hasRelatedWork W2957776456 @default.
- W3200659275 hasRelatedWork W3022038857 @default.
- W3200659275 hasRelatedWork W3088315509 @default.
- W3200659275 hasRelatedWork W3209094908 @default.
- W3200659275 hasRelatedWork W4210912933 @default.
- W3200659275 hasRelatedWork W4255994452 @default.
- W3200659275 hasRelatedWork W4319083788 @default.
- W3200659275 hasRelatedWork W4361026739 @default.
- W3200659275 hasRelatedWork W4379471189 @default.
- W3200659275 isParatext "false" @default.