Cold-Start Reinforcement Learning with Softmax Policy Gradient

Code

• github.com/jacksonchen1998/Cold-Start-Reinforcement-Learning-with-Softmax-Policy-Gradient
  pytorch★ 0

Abstract

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 value function 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.

Tasks

Reproductions