Dataset Groups Activity Stream REBEL REBEL is a dataset for reward regularization based robotic reinforcement learning from human feedback. BibTex: @dataset{Souradip_Chakraborty_and_Amisha_Bhaskar_and_Anukriti_Singh_and_Pratap_Tokekar_and_Dinesh_Manocha_and_Amrit_Singh_Bedi_2024, abstract = {REBEL is a dataset for reward regularization based robotic reinforcement learning from human feedback.}, author = {Souradip Chakraborty and Amisha Bhaskar and Anukriti Singh and Pratap Tokekar and Dinesh Manocha and Amrit Singh Bedi}, doi = {10.57702/vlcfspil}, institution = {No Organization}, keyword = {'Human Feedback', 'Reward Regularization', 'Robotic Reinforcement Learning'}, month = {dec}, publisher = {TIB}, title = {REBEL}, url = {https://service.tib.eu/ldmservice/dataset/rebel}, year = {2024} }
