- 3.ZipRecruiter on Classifying Job Titles With Noisy Labels Using REINFORCE - Fine-grained job title classification with noisy labels using the REINFORCE algorithm and multi-task learning
- 1.this article has a very nice trick in adding a reward component to the loss function in order to mitigate for unbalanced class label problem, instead of the usual balancing.
- Markov chain problem, (state, action, new state, reward)
- Lots of Exploration in the beginning, then exploitation
- Returns optimal policy.