@article{ma2024eureka,
      title={Eureka: Human-Level Reward Design via Coding Large Language Models}, 
      author={Yecheng Jason Ma and William Liang and Guanzhi Wang and De-An Huang and Osbert Bastani and Dinesh Jayaraman and Yuke Zhu and Linxi Fan and Anima Anandkumar},
      year={2024},
      journal={ICLR}
}

{"_id":"Q84DA6joFqYPRCmrv","bibbaseid":"ma-liang-wang-huang-bastani-jayaraman-zhu-fan-etal-eurekahumanlevelrewarddesignviacodinglargelanguagemodels-2024","author_short":["Ma, Y. J.","Liang, W.","Wang, G.","Huang, D.","Bastani, O.","Jayaraman, D.","Zhu, Y.","Fan, L.","Anandkumar, A."],"bibdata":{"bibtype":"article","type":"article","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","author":[{"firstnames":["Yecheng","Jason"],"propositions":[],"lastnames":["Ma"],"suffixes":[]},{"firstnames":["William"],"propositions":[],"lastnames":["Liang"],"suffixes":[]},{"firstnames":["Guanzhi"],"propositions":[],"lastnames":["Wang"],"suffixes":[]},{"firstnames":["De-An"],"propositions":[],"lastnames":["Huang"],"suffixes":[]},{"firstnames":["Osbert"],"propositions":[],"lastnames":["Bastani"],"suffixes":[]},{"firstnames":["Dinesh"],"propositions":[],"lastnames":["Jayaraman"],"suffixes":[]},{"firstnames":["Yuke"],"propositions":[],"lastnames":["Zhu"],"suffixes":[]},{"firstnames":["Linxi"],"propositions":[],"lastnames":["Fan"],"suffixes":[]},{"firstnames":["Anima"],"propositions":[],"lastnames":["Anandkumar"],"suffixes":[]}],"year":"2024","journal":"ICLR","bibtex":"@article{ma2024eureka,\n title={Eureka: Human-Level Reward Design via Coding Large Language Models}, \n author={Yecheng Jason Ma and William Liang and Guanzhi Wang and De-An Huang and Osbert Bastani and Dinesh Jayaraman and Yuke Zhu and Linxi Fan and Anima Anandkumar},\n year={2024},\n journal={ICLR}\n}\n","author_short":["Ma, Y. J.","Liang, W.","Wang, G.","Huang, D.","Bastani, O.","Jayaraman, D.","Zhu, Y.","Fan, L.","Anandkumar, A."],"key":"ma2024eureka","id":"ma2024eureka","bibbaseid":"ma-liang-wang-huang-bastani-jayaraman-zhu-fan-etal-eurekahumanlevelrewarddesignviacodinglargelanguagemodels-2024","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://gist.githubusercontent.com/dineshj1/0185709a89b3de5cb7c763e36c0cb031/raw/","dataSources":["azLig8QfcbeEgFsYA"],"keywords":[],"search_terms":["eureka","human","level","reward","design","via","coding","large","language","models","ma","liang","wang","huang","bastani","jayaraman","zhu","fan","anandkumar"],"title":"Eureka: Human-Level Reward Design via Coding Large Language Models","year":2024}