Reinforcement Learning
Last updated
Last updated
& completed
Vidhya on
Vidhya on
ZipRecruiter on - Fine-grained job title classification with noisy labels using the REINFORCE algorithm and multi-task learning
-> 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.
David Silver - -
book
Markov chain problem, (state, action, new state, reward)
Lots of Exploration in the beginning, then exploitation
Returns optimal policy.
Refer to youtube
Pytorch