Matches in SemOpenAlex for { <https://semopenalex.org/work/W2914702425> ?p ?o ?g. }
- W2914702425 endingPage "103949" @default.
- W2914702425 startingPage "103949" @default.
- W2914702425 abstract "Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying requirements as tasks or goals. We propose a model-free RL algorithm that enables the use of Linear Temporal Logic (LTL) to formulate a goal for unknown continuous-state/action Markov Decision Processes (MDPs). The given LTL property is translated into a Limit-Deterministic Generalised Büchi Automaton (LDGBA), which is then used to shape a synchronous reward function on-the-fly. Under certain assumptions, the algorithm is guaranteed to synthesise a control policy whose traces satisfy the LTL specification with maximal probability." @default.
- W2914702425 created "2019-02-21" @default.
- W2914702425 creator A5085342880 @default.
- W2914702425 creator A5086206346 @default.
- W2914702425 creator A5091718585 @default.
- W2914702425 date "2023-05-01" @default.
- W2914702425 modified "2023-09-25" @default.
- W2914702425 title "Certified Reinforcement Learning with Logic Guidance" @default.
- W2914702425 cites W106517363 @default.
- W2914702425 cites W1492507105 @default.
- W2914702425 cites W1499021164 @default.
- W2914702425 cites W1512937499 @default.
- W2914702425 cites W1520127302 @default.
- W2914702425 cites W1540883472 @default.
- W2914702425 cites W1547105496 @default.
- W2914702425 cites W1552830313 @default.
- W2914702425 cites W1556387789 @default.
- W2914702425 cites W1557517019 @default.
- W2914702425 cites W1617322827 @default.
- W2914702425 cites W166862392 @default.
- W2914702425 cites W169931978 @default.
- W2914702425 cites W1862398452 @default.
- W2914702425 cites W1967294943 @default.
- W2914702425 cites W1977444293 @default.
- W2914702425 cites W1982650427 @default.
- W2914702425 cites W1983264093 @default.
- W2914702425 cites W1983497631 @default.
- W2914702425 cites W1988115241 @default.
- W2914702425 cites W1992689405 @default.
- W2914702425 cites W1993536119 @default.
- W2914702425 cites W2017419329 @default.
- W2914702425 cites W2018087463 @default.
- W2914702425 cites W2023808162 @default.
- W2914702425 cites W2031592188 @default.
- W2914702425 cites W2046637502 @default.
- W2914702425 cites W2055647224 @default.
- W2914702425 cites W2060248504 @default.
- W2914702425 cites W2061372038 @default.
- W2914702425 cites W2067718333 @default.
- W2914702425 cites W2076337359 @default.
- W2914702425 cites W2080813827 @default.
- W2914702425 cites W2084838588 @default.
- W2914702425 cites W2105964247 @default.
- W2914702425 cites W2111093520 @default.
- W2914702425 cites W2113501460 @default.
- W2914702425 cites W2119007372 @default.
- W2914702425 cites W2121110499 @default.
- W2914702425 cites W2137983211 @default.
- W2914702425 cites W2145339207 @default.
- W2914702425 cites W2157807654 @default.
- W2914702425 cites W2178626170 @default.
- W2914702425 cites W2222789563 @default.
- W2914702425 cites W2257979135 @default.
- W2914702425 cites W2288565641 @default.
- W2914702425 cites W2405166594 @default.
- W2914702425 cites W2487186542 @default.
- W2914702425 cites W2489939061 @default.
- W2914702425 cites W2499588876 @default.
- W2914702425 cites W2501722818 @default.
- W2914702425 cites W2521432080 @default.
- W2914702425 cites W2567705466 @default.
- W2914702425 cites W2575705757 @default.
- W2914702425 cites W2590126170 @default.
- W2914702425 cites W2623730681 @default.
- W2914702425 cites W2739508666 @default.
- W2914702425 cites W2744647809 @default.
- W2914702425 cites W2745094767 @default.
- W2914702425 cites W2787908307 @default.
- W2914702425 cites W2895196950 @default.
- W2914702425 cites W2912198824 @default.
- W2914702425 cites W2936953762 @default.
- W2914702425 cites W2950176007 @default.
- W2914702425 cites W2952908521 @default.
- W2914702425 cites W2953302092 @default.
- W2914702425 cites W2963575966 @default.
- W2914702425 cites W2963604565 @default.
- W2914702425 cites W2963778636 @default.
- W2914702425 cites W2963907727 @default.
- W2914702425 cites W2964227312 @default.
- W2914702425 cites W2966537673 @default.
- W2914702425 cites W296769721 @default.
- W2914702425 cites W297821776 @default.
- W2914702425 cites W3011250830 @default.
- W2914702425 cites W3026873144 @default.
- W2914702425 cites W3039276491 @default.
- W2914702425 cites W3043774672 @default.
- W2914702425 cites W3046763300 @default.
- W2914702425 cites W3080598349 @default.
- W2914702425 cites W3090827750 @default.
- W2914702425 cites W3100944043 @default.
- W2914702425 cites W3104013016 @default.
- W2914702425 cites W3104303413 @default.
- W2914702425 cites W3106238320 @default.
- W2914702425 cites W3119337186 @default.
- W2914702425 cites W3120789931 @default.
- W2914702425 cites W3121275971 @default.
- W2914702425 cites W3125631598 @default.
- W2914702425 cites W3125855560 @default.