Dataset Groups Activity Stream Soft Actor-Critic A soft actor-critic algorithm for off-policy maximum entropy deep reinforcement learning. BibTex: @dataset{Tuomas_Haarnoja_and_Aurick_Zhou_and_Pieter_Abbeel_and_Sergey_Levine_2024, abstract = {A soft actor-critic algorithm for off-policy maximum entropy deep reinforcement learning.}, author = {Tuomas Haarnoja and Aurick Zhou and Pieter Abbeel and Sergey Levine}, doi = {10.57702/rd6rjeug}, institution = {No Organization}, keyword = {'actor-critic', 'maximum entropy reinforcement learning', 'off-policy learning'}, month = {dec}, publisher = {TIB}, title = {Soft Actor-Critic}, url = {https://service.tib.eu/ldmservice/dataset/soft-actor-critic}, year = {2024} }