FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200372272> ?p ?o ?g. }

• W3200372272 endingPage "3644" @default.
• W3200372272 startingPage "3621" @default.
• W3200372272 abstract "A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However, there is a general lack of collaboration or interoperability between different approaches using external information. In this work, while reviewing externally-influenced methods, we propose a conceptual framework and taxonomy for assisted reinforcement learning, aimed at fostering collaboration by classifying and comparing various methods that use external information in the learning process. The proposed taxonomy details the relationship between the external information source and the learner agent, highlighting the process of information decomposition, structure, retention, and how it can be used to influence agent learning. As well as reviewing state-of-the-art methods, we identify current streams of reinforcement learning that use external information in order to improve the agent’s performance and its decision-making process. These include heuristic reinforcement learning, interactive reinforcement learning, learning from demonstration, transfer learning, and learning from multiple sources, among others. These streams of reinforcement learning operate with the shared objective of scaffolding the learner agent. Lastly, we discuss further possibilities for future work in the field of assisted reinforcement learning systems." @default.
• W3200372272 created "2021-09-27" @default.
• W3200372272 creator A5013402425 @default.
• W3200372272 creator A5032749222 @default.
• W3200372272 creator A5044098673 @default.
• W3200372272 creator A5070914351 @default.
• W3200372272 creator A5080095540 @default.
• W3200372272 creator A5084002137 @default.
• W3200372272 creator A5091862657 @default.
• W3200372272 date "2021-09-18" @default.
• W3200372272 modified "2023-10-18" @default.
• W3200372272 title "A conceptual framework for externally-influenced agents: an assisted reinforcement learning review" @default.
• W3200372272 cites W1566652554 @default.
• W3200372272 cites W1655830068 @default.
• W3200372272 cites W1862757251 @default.
• W3200372272 cites W1963873191 @default.
• W3200372272 cites W1965568826 @default.
• W3200372272 cites W1966259872 @default.
• W3200372272 cites W1969685488 @default.
• W3200372272 cites W1977655452 @default.
• W3200372272 cites W1986014385 @default.
• W3200372272 cites W1999549166 @default.
• W3200372272 cites W1999874108 @default.
• W3200372272 cites W2031727428 @default.
• W3200372272 cites W2041367235 @default.
• W3200372272 cites W2070410573 @default.
• W3200372272 cites W2081030963 @default.
• W3200372272 cites W2093192040 @default.
• W3200372272 cites W2093313552 @default.
• W3200372272 cites W2097113539 @default.
• W3200372272 cites W2104308387 @default.
• W3200372272 cites W2107726111 @default.
• W3200372272 cites W2129659607 @default.
• W3200372272 cites W2132504164 @default.
• W3200372272 cites W2141925681 @default.
• W3200372272 cites W2148472461 @default.
• W3200372272 cites W2154328025 @default.
• W3200372272 cites W2154633587 @default.
• W3200372272 cites W2156578004 @default.
• W3200372272 cites W2156869222 @default.
• W3200372272 cites W2157174816 @default.
• W3200372272 cites W2158235281 @default.
• W3200372272 cites W2171578145 @default.
• W3200372272 cites W2202549229 @default.
• W3200372272 cites W2296073425 @default.
• W3200372272 cites W2300445845 @default.
• W3200372272 cites W2491167697 @default.
• W3200372272 cites W2551398049 @default.
• W3200372272 cites W2559960928 @default.
• W3200372272 cites W2565110810 @default.
• W3200372272 cites W2625456521 @default.
• W3200372272 cites W2741594138 @default.
• W3200372272 cites W2759847408 @default.
• W3200372272 cites W2788388592 @default.
• W3200372272 cites W2792217087 @default.
• W3200372272 cites W2794066724 @default.
• W3200372272 cites W2795786572 @default.
• W3200372272 cites W2883246952 @default.
• W3200372272 cites W2883750587 @default.
• W3200372272 cites W2895806276 @default.
• W3200372272 cites W2911667635 @default.
• W3200372272 cites W2912947802 @default.
• W3200372272 cites W2914358862 @default.
• W3200372272 cites W2921955147 @default.
• W3200372272 cites W2944766483 @default.
• W3200372272 cites W2957624498 @default.
• W3200372272 cites W2963099939 @default.
• W3200372272 cites W2963523627 @default.
• W3200372272 cites W2963890729 @default.
• W3200372272 cites W2967503703 @default.
• W3200372272 cites W2978938326 @default.
• W3200372272 cites W2996868001 @default.
• W3200372272 cites W2998396902 @default.
• W3200372272 cites W3000965188 @default.
• W3200372272 cites W3039116038 @default.
• W3200372272 cites W3039772337 @default.
• W3200372272 cites W3041133507 @default.
• W3200372272 cites W3043075313 @default.
• W3200372272 cites W3048135502 @default.
• W3200372272 cites W3090570651 @default.
• W3200372272 cites W3096621767 @default.
• W3200372272 cites W3099324303 @default.
• W3200372272 cites W3100285570 @default.
• W3200372272 cites W3101926919 @default.
• W3200372272 cites W3103262232 @default.
• W3200372272 cites W3112469726 @default.
• W3200372272 cites W3124474911 @default.
• W3200372272 cites W3126966255 @default.
• W3200372272 cites W3186035148 @default.
• W3200372272 cites W3198115943 @default.
• W3200372272 cites W3198729202 @default.
• W3200372272 cites W4246078117 @default.
• W3200372272 cites W605348272 @default.
• W3200372272 cites W8222043 @default.
• W3200372272 doi "https://doi.org/10.1007/s12652-021-03489-y" @default.
• W3200372272 hasPublicationYear "2021" @default.
• W3200372272 type Work @default.
• W3200372272 sameAs 3200372272 @default.

• next