Reviews: Cold-Start Reinforcement Learning with Softmax Policy Gradient

The paper presents a new method for structured output prediction using reinforcement learning. Previous methods used reward augmented maximum likelihoods or policy gradients. The new method uses a soft-max objective. The authors present a new inference method that can be used to efficiently evaluate the integral in the objective. In addition, the authors propose to use additional reward functions which encode prior knowledge (e.g. to avoid word repetitions).