Reinforcement Learning

  1. 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.

Q-LEARN

  • Markov chain problem, (state, action, new state, reward)

  • Lots of Exploration in the beginning, then exploitation

  • Returns optimal policy.

  • Refer to youtube here

Deep Learning

RLHF

Last updated