Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037221466> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W3037221466 endingPage "1950" @default.
- W3037221466 startingPage "1949" @default.
- W3037221466 abstract "Inverse reinforcement learning is a method that estates a reward function from experts demonstrations. Most existing inverse reinforcement learning methods assume that an expert gives demonstrations in a fixed environment, although the expert can provide demonstrations for a specific objective in multiple environments. In such cases, normal practice is to use demonstrations in multiple environments to estimate the expert's reward. Herein, we formulate this problem based on a Bayesian inverse reinforcement learning framework and propose a mini-batch Markov chain Monte Carlo method. An advantage of our method is scalability. Our proposed method is scalable with respect to a number of environments in which expert demonstrations are generated. Experimental results show quantitatively that the proposed method outperforms existing inverse reinforcement learning methods." @default.
- W3037221466 created "2020-07-02" @default.
- W3037221466 creator A5047470756 @default.
- W3037221466 creator A5067041561 @default.
- W3037221466 date "2020-05-05" @default.
- W3037221466 modified "2023-09-26" @default.
- W3037221466 title "Mini-batch Bayesian Inverse Reinforcement Learning for Multiple Dynamics" @default.
- W3037221466 cites W1591675293 @default.
- W3037221466 hasPublicationYear "2020" @default.
- W3037221466 type Work @default.
- W3037221466 sameAs 3037221466 @default.
- W3037221466 citedByCount "0" @default.
- W3037221466 crossrefType "proceedings-article" @default.
- W3037221466 hasAuthorship W3037221466A5047470756 @default.
- W3037221466 hasAuthorship W3037221466A5067041561 @default.
- W3037221466 hasConcept C107673813 @default.
- W3037221466 hasConcept C111350023 @default.
- W3037221466 hasConcept C119857082 @default.
- W3037221466 hasConcept C154945302 @default.
- W3037221466 hasConcept C207467116 @default.
- W3037221466 hasConcept C2524010 @default.
- W3037221466 hasConcept C33923547 @default.
- W3037221466 hasConcept C41008148 @default.
- W3037221466 hasConcept C48044578 @default.
- W3037221466 hasConcept C77088390 @default.
- W3037221466 hasConcept C97541855 @default.
- W3037221466 hasConcept C98763669 @default.
- W3037221466 hasConceptScore W3037221466C107673813 @default.
- W3037221466 hasConceptScore W3037221466C111350023 @default.
- W3037221466 hasConceptScore W3037221466C119857082 @default.
- W3037221466 hasConceptScore W3037221466C154945302 @default.
- W3037221466 hasConceptScore W3037221466C207467116 @default.
- W3037221466 hasConceptScore W3037221466C2524010 @default.
- W3037221466 hasConceptScore W3037221466C33923547 @default.
- W3037221466 hasConceptScore W3037221466C41008148 @default.
- W3037221466 hasConceptScore W3037221466C48044578 @default.
- W3037221466 hasConceptScore W3037221466C77088390 @default.
- W3037221466 hasConceptScore W3037221466C97541855 @default.
- W3037221466 hasConceptScore W3037221466C98763669 @default.
- W3037221466 hasLocation W30372214661 @default.
- W3037221466 hasOpenAccess W3037221466 @default.
- W3037221466 hasPrimaryLocation W30372214661 @default.
- W3037221466 hasRelatedWork W2105156548 @default.
- W3037221466 hasRelatedWork W2139586486 @default.
- W3037221466 hasRelatedWork W2143680741 @default.
- W3037221466 hasRelatedWork W2211996086 @default.
- W3037221466 hasRelatedWork W224030514 @default.
- W3037221466 hasRelatedWork W2348899667 @default.
- W3037221466 hasRelatedWork W2558359316 @default.
- W3037221466 hasRelatedWork W2727668055 @default.
- W3037221466 hasRelatedWork W2803590301 @default.
- W3037221466 hasRelatedWork W2950226226 @default.
- W3037221466 hasRelatedWork W2963622537 @default.
- W3037221466 hasRelatedWork W2963817681 @default.
- W3037221466 hasRelatedWork W3035470936 @default.
- W3037221466 hasRelatedWork W3087585308 @default.
- W3037221466 hasRelatedWork W3135573334 @default.
- W3037221466 hasRelatedWork W3175819369 @default.
- W3037221466 hasRelatedWork W3185097486 @default.
- W3037221466 hasRelatedWork W3204552159 @default.
- W3037221466 hasRelatedWork W3207977358 @default.
- W3037221466 hasRelatedWork W5547603 @default.
- W3037221466 isParatext "false" @default.
- W3037221466 isRetracted "false" @default.
- W3037221466 magId "3037221466" @default.
- W3037221466 workType "article" @default.