FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3152257860> ?p ?o ?g. }

• W3152257860 abstract "Modern navigation algorithms based on deep reinforcement learning (RL) show promising efficiency and robustness. However, most deep RL algorithms operate in a risk-neutral manner, making no special attempt to shield users from relatively rare but serious outcomes, even if such shielding might cause little loss of performance. Furthermore, such algorithms typically make no provisions to ensure safety in the presence of inaccuracies in the models on which they were trained, beyond adding a cost-of-collision and some domain randomization while training, in spite of the formidable complexity of the environments in which they operate. In this paper, we present a novel distributional RL algorithm that not only learns an uncertainty-aware policy, but can also change its risk measure without expensive fine-tuning or retraining. Our method shows superior performance and safety over baselines in partially-observed navigation tasks. We also demonstrate that agents trained using our method can adapt their policies to a wide range of risk measures at run-time." @default.
• W3152257860 created "2021-04-13" @default.
• W3152257860 creator A5000827821 @default.
• W3152257860 creator A5025448979 @default.
• W3152257860 creator A5043643745 @default.
• W3152257860 creator A5055862728 @default.
• W3152257860 creator A5085010633 @default.
• W3152257860 date "2021-04-07" @default.
• W3152257860 modified "2023-09-26" @default.
• W3152257860 title "Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation" @default.
• W3152257860 cites W1845972764 @default.
• W3152257860 cites W1999131722 @default.
• W3152257860 cites W2011418219 @default.
• W3152257860 cites W2019291268 @default.
• W3152257860 cites W2056819186 @default.
• W3152257860 cites W2102288976 @default.
• W3152257860 cites W2133469585 @default.
• W3152257860 cites W2604216058 @default.
• W3152257860 cites W2744921762 @default.
• W3152257860 cites W2764297211 @default.
• W3152257860 cites W2766447205 @default.
• W3152257860 cites W2781726626 @default.
• W3152257860 cites W2786036274 @default.
• W3152257860 cites W2798705390 @default.
• W3152257860 cites W2803308811 @default.
• W3152257860 cites W2807095006 @default.
• W3152257860 cites W2891045506 @default.
• W3152257860 cites W2904246096 @default.
• W3152257860 cites W2905224739 @default.
• W3152257860 cites W2912063360 @default.
• W3152257860 cites W2913878882 @default.
• W3152257860 cites W2952023104 @default.
• W3152257860 cites W2962917939 @default.
• W3152257860 cites W2963423916 @default.
• W3152257860 cites W2963590277 @default.
• W3152257860 cites W2963757175 @default.
• W3152257860 cites W2963821308 @default.
• W3152257860 cites W2963938771 @default.
• W3152257860 cites W2964059111 @default.
• W3152257860 cites W2964199361 @default.
• W3152257860 cites W2968104655 @default.
• W3152257860 cites W2970036354 @default.
• W3152257860 cites W2981030070 @default.
• W3152257860 cites W3021487874 @default.
• W3152257860 cites W3034379033 @default.
• W3152257860 cites W3090307871 @default.
• W3152257860 cites W3090935992 @default.
• W3152257860 cites W3091067209 @default.
• W3152257860 cites W3091442961 @default.
• W3152257860 cites W3091453879 @default.
• W3152257860 cites W3101441984 @default.
• W3152257860 cites W3108970058 @default.
• W3152257860 cites W3119924655 @default.
• W3152257860 cites W3129986830 @default.
• W3152257860 hasPublicationYear "2021" @default.
• W3152257860 type Work @default.
• W3152257860 sameAs 3152257860 @default.
• W3152257860 citedByCount "1" @default.
• W3152257860 countsByYear W31522578602021 @default.
• W3152257860 crossrefType "posted-content" @default.
• W3152257860 hasAuthorship W3152257860A5000827821 @default.
• W3152257860 hasAuthorship W3152257860A5025448979 @default.
• W3152257860 hasAuthorship W3152257860A5043643745 @default.
• W3152257860 hasAuthorship W3152257860A5055862728 @default.
• W3152257860 hasAuthorship W3152257860A5085010633 @default.
• W3152257860 hasConcept C104317684 @default.
• W3152257860 hasConcept C119857082 @default.
• W3152257860 hasConcept C121704057 @default.
• W3152257860 hasConcept C144133560 @default.
• W3152257860 hasConcept C154945302 @default.
• W3152257860 hasConcept C155202549 @default.
• W3152257860 hasConcept C185592680 @default.
• W3152257860 hasConcept C2776654903 @default.
• W3152257860 hasConcept C2778712577 @default.
• W3152257860 hasConcept C38652104 @default.
• W3152257860 hasConcept C41008148 @default.
• W3152257860 hasConcept C55493867 @default.
• W3152257860 hasConcept C63479239 @default.
• W3152257860 hasConcept C97541855 @default.
• W3152257860 hasConceptScore W3152257860C104317684 @default.
• W3152257860 hasConceptScore W3152257860C119857082 @default.
• W3152257860 hasConceptScore W3152257860C121704057 @default.
• W3152257860 hasConceptScore W3152257860C144133560 @default.
• W3152257860 hasConceptScore W3152257860C154945302 @default.
• W3152257860 hasConceptScore W3152257860C155202549 @default.
• W3152257860 hasConceptScore W3152257860C185592680 @default.
• W3152257860 hasConceptScore W3152257860C2776654903 @default.
• W3152257860 hasConceptScore W3152257860C2778712577 @default.
• W3152257860 hasConceptScore W3152257860C38652104 @default.
• W3152257860 hasConceptScore W3152257860C41008148 @default.
• W3152257860 hasConceptScore W3152257860C55493867 @default.
• W3152257860 hasConceptScore W3152257860C63479239 @default.
• W3152257860 hasConceptScore W3152257860C97541855 @default.
• W3152257860 hasLocation W31522578601 @default.
• W3152257860 hasOpenAccess W3152257860 @default.
• W3152257860 hasPrimaryLocation W31522578601 @default.
• W3152257860 hasRelatedWork W2890211540 @default.
• W3152257860 hasRelatedWork W2904450917 @default.
• W3152257860 hasRelatedWork W2955766841 @default.
• W3152257860 hasRelatedWork W2962749646 @default.

• next