We are announcing the release of our state-of-the-art off-policy model-free reinforcement learning algorithm, soft actor-critic (SAC). This algorithm has been developed jointly at UC Berkeley and Google Brain, and we have been using it internally for our robotics experiment.
This is a companion discussion for the article “Soft Actor Critic—Deep Reinforcement Learning with Real-World Robots – - https://bair.berkeley.edu/blog/2018/12/14/sac/” submitted on the community's news feed.
Reply to this topic to share your thoughts on this article.