HN user

jac08h

47 karma
Posts10
Comments13
View on HN

While studying for an RL course, I created a reference for several algorithms with a brief description of what limitations they solve. Example:

Problem: SARSA pushes q-values towards the current policy, but ideally we'd want optimal values. Solution: Use the best action in TD-target calculation -> Q-learning

Perhaps someone else will find it helpful!