Dataset Groups Activity Stream RL Boosting via Weak Supervised Learning The dataset used in the paper is a reinforcement learning dataset, where the goal is to learn a policy that maximizes the expected return in a Markov decision process. BibTex: @dataset{Nataly_Brukhim_and_Elad_Hazan_and_Karan_Singh_2024, abstract = {The dataset used in the paper is a reinforcement learning dataset, where the goal is to learn a policy that maximizes the expected return in a Markov decision process.}, author = {Nataly Brukhim and Elad Hazan and Karan Singh}, doi = {10.57702/41b5lzqf}, institution = {No Organization}, keyword = {'Boosting', 'RL', 'Supervised Learning'}, month = {dec}, publisher = {TIB}, title = {RL Boosting via Weak Supervised Learning}, url = {https://service.tib.eu/ldmservice/dataset/rl-boosting-via-weak-supervised-learning}, year = {2024} }
