Cold-Start Reinforcement Learning with Softmax Policy Gradients

Policy-gradient approaches to reinforcement learning have two common and
undesirable overhead procedures, namely warm-start training and sample variance
reduction. In this paper, we describe a reinforcement learning method based on
a softmax policy that requires neither of these procedures. Our method combines
the advantages of policy-gradient methods with the efficiency and simplicity of
maximum-likelihood approaches. We apply this new cold-start reinforcement
learning method in training sequence generation models for structured output
prediction problems. Empirical evidence validates this method on automatic
summarization and image captioning tasks.

• Machine Intelligence