4.3k citations · 15.5k across the 33 of their papers we have counts for
3 papers · 1 filter
Gradient Estimation Using Stochastic Computation Graphs
John Schulman, Nicolas Heess, Theophane Weber +1
In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables,…
High-Dimensional Continuous Control Using Generalized Advantage Estimation
John Schulman, Philipp Moritz, Sergey Levine +2
Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear fu…
Trust Region Policy Optimization
John Schulman, Sergey Levine, Philipp Moritz +2
We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we dev…