Tweeted By @svlevine
Can we use reinforcement learning together with search to solve temporally extended tasks? In Search on the Replay Buffer (w/ Ben Eysenbach and @rsalakhu), we use goal-conditioned policies to build a graph for search.
— Sergey Levine (@svlevine) June 13, 2019
Paper: https://t.co/qMEHyU06mU
Colab: https://t.co/jqADqWeJEu