@article{2481,
  author = {Donghao Li and Ruiquan Huang and Cong Shen and Jing Yang},
  title = {Near-optimal Conservative Exploration in Reinforcement Learning under
  Episode-wise Constraints},
  year = {2023},
  journal = {arXiv (Cornell University)},
  url = {https://arxiv.org/abs/2306.06265}
}

{"_id":"jNDxSca8XtJoAvhPN","bibbaseid":"li-huang-shen-yang-nearoptimalconservativeexplorationinreinforcementlearningunderepisodewiseconstraints-2023","author_short":["Li, D.","Huang, R.","Shen, C.","Yang, J."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Donghao"],"propositions":[],"lastnames":["Li"],"suffixes":[]},{"firstnames":["Ruiquan"],"propositions":[],"lastnames":["Huang"],"suffixes":[]},{"firstnames":["Cong"],"propositions":[],"lastnames":["Shen"],"suffixes":[]},{"firstnames":["Jing"],"propositions":[],"lastnames":["Yang"],"suffixes":[]}],"title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","year":"2023","journal":"arXiv (Cornell University)","url":"https://arxiv.org/abs/2306.06265","bibtex":"@article{2481,\n author = {Donghao Li and Ruiquan Huang and Cong Shen and Jing Yang},\n title = {Near-optimal Conservative Exploration in Reinforcement Learning under\n Episode-wise Constraints},\n year = {2023},\n journal = {arXiv (Cornell University)},\n url = {https://arxiv.org/abs/2306.06265}\n}\n\n","author_short":["Li, D.","Huang, R.","Shen, C.","Yang, J."],"key":"2481","id":"2481","bibbaseid":"li-huang-shen-yang-nearoptimalconservativeexplorationinreinforcementlearningunderepisodewiseconstraints-2023","role":"author","urls":{"Paper":"https://arxiv.org/abs/2306.06265"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/f/fFERMKNwKyHLsDPJ3/Link_Lab_Publications.bib","dataSources":["mwAui9iKniQyhTc49","RbCkvcfqfbgtxTyNT"],"keywords":[],"search_terms":["near","optimal","conservative","exploration","reinforcement","learning","under","episode","wise","constraints","li","huang","shen","yang"],"title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","year":2023}