Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134238439> ?p ?o ?g. }
- W3134238439 abstract "Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agents calls for a deeper understanding of information acquisition and representation. We discuss concepts and regret analysis that together offer principled guidance. This line of thinking sheds light on questions of what information to seek, how to seek that information, and what information to retain. To illustrate concepts, we design simple agents that build on them and present computational results that highlight data efficiency." @default.
- W3134238439 created "2021-03-15" @default.
- W3134238439 creator A5015899120 @default.
- W3134238439 creator A5027358754 @default.
- W3134238439 creator A5027959626 @default.
- W3134238439 creator A5045543562 @default.
- W3134238439 creator A5067555437 @default.
- W3134238439 creator A5085692306 @default.
- W3134238439 date "2021-03-06" @default.
- W3134238439 modified "2023-09-25" @default.
- W3134238439 title "Reinforcement Learning, Bit by Bit" @default.
- W3134238439 cites W146611155 @default.
- W3134238439 cites W1497039698 @default.
- W3134238439 cites W1569296262 @default.
- W3134238439 cites W1570690983 @default.
- W3134238439 cites W1575592356 @default.
- W3134238439 cites W1582436621 @default.
- W3134238439 cites W1625390266 @default.
- W3134238439 cites W1714211023 @default.
- W3134238439 cites W1757796397 @default.
- W3134238439 cites W1862757251 @default.
- W3134238439 cites W1973885534 @default.
- W3134238439 cites W1977898558 @default.
- W3134238439 cites W1988360637 @default.
- W3134238439 cites W2001863269 @default.
- W3134238439 cites W2003996846 @default.
- W3134238439 cites W2009551863 @default.
- W3134238439 cites W2016647253 @default.
- W3134238439 cites W2039522160 @default.
- W3134238439 cites W2041367235 @default.
- W3134238439 cites W2049934117 @default.
- W3134238439 cites W2054940200 @default.
- W3134238439 cites W2067352298 @default.
- W3134238439 cites W2069034916 @default.
- W3134238439 cites W2091565802 @default.
- W3134238439 cites W2100677568 @default.
- W3134238439 cites W2103626435 @default.
- W3134238439 cites W2111764152 @default.
- W3134238439 cites W2121863487 @default.
- W3134238439 cites W2132622533 @default.
- W3134238439 cites W2132849848 @default.
- W3134238439 cites W2145339207 @default.
- W3134238439 cites W2149721706 @default.
- W3134238439 cites W2156974606 @default.
- W3134238439 cites W2158282517 @default.
- W3134238439 cites W2167433878 @default.
- W3134238439 cites W2168405694 @default.
- W3134238439 cites W2332257675 @default.
- W3134238439 cites W2548195524 @default.
- W3134238439 cites W2561776174 @default.
- W3134238439 cites W2624731731 @default.
- W3134238439 cites W2765733960 @default.
- W3134238439 cites W2769648743 @default.
- W3134238439 cites W2791950347 @default.
- W3134238439 cites W2805217655 @default.
- W3134238439 cites W2884559200 @default.
- W3134238439 cites W2904591482 @default.
- W3134238439 cites W2947200456 @default.
- W3134238439 cites W2962723954 @default.
- W3134238439 cites W2962901934 @default.
- W3134238439 cites W2963007936 @default.
- W3134238439 cites W2963049774 @default.
- W3134238439 cites W2963158178 @default.
- W3134238439 cites W2963158889 @default.
- W3134238439 cites W2963350293 @default.
- W3134238439 cites W2963373419 @default.
- W3134238439 cites W2963751259 @default.
- W3134238439 cites W2963938771 @default.
- W3134238439 cites W2964000194 @default.
- W3134238439 cites W2964083594 @default.
- W3134238439 cites W2964121744 @default.
- W3134238439 cites W2966101885 @default.
- W3134238439 cites W2966286942 @default.
- W3134238439 cites W2970717270 @default.
- W3134238439 cites W2970925994 @default.
- W3134238439 cites W2974778612 @default.
- W3134238439 cites W2978435634 @default.
- W3134238439 cites W2996070979 @default.
- W3134238439 cites W2996558820 @default.
- W3134238439 cites W3007682568 @default.
- W3134238439 cites W3011120880 @default.
- W3134238439 cites W3037319563 @default.
- W3134238439 cites W3087776591 @default.
- W3134238439 cites W3091830134 @default.
- W3134238439 cites W3102223710 @default.
- W3134238439 cites W3118210634 @default.
- W3134238439 cites W3123298421 @default.
- W3134238439 cites W3123638774 @default.
- W3134238439 cites W3124703814 @default.
- W3134238439 cites W3131850260 @default.
- W3134238439 cites W3150304496 @default.
- W3134238439 cites W567721252 @default.
- W3134238439 doi "https://doi.org/10.48550/arxiv.2103.04047" @default.
- W3134238439 hasPublicationYear "2021" @default.
- W3134238439 type Work @default.
- W3134238439 sameAs 3134238439 @default.
- W3134238439 citedByCount "3" @default.
- W3134238439 countsByYear W31342384392021 @default.
- W3134238439 crossrefType "posted-content" @default.
- W3134238439 hasAuthorship W3134238439A5015899120 @default.