Join GitHub today
GitHub is home to over 40 million developers working together to host and review code, manage projects, and build software together.Sign up
RL4J - Extracted TD Target calculations (StandardDQN and DoubleDQN) #8267
What changes were proposed in this pull request?
In this PR, I extracted the TD Target calculations (Standard DQN and Double DQN) from QLearningDiscrete to a bunch of more focused components. First, this should help us when we'll add new algorithms.
The way it's plugged in QLearningDiscrete is not perfect but, I'd like to make smaller PRs so, I only made minimal changes to QLearningDiscrete.
How was this patch tested?
unit tests and manual tests
The following checklist helps ensure your PR is complete:
Ok, I see. If you don't mind, I'll do the fix in another PR; I'd like to not just fix