A reinforcement learning package for Julia
Role in this project:
ML Engineer Contributions:1 review, 5 commits, 5 PRs in 4 days
Contributions summary:Mo contributed to the reinforcement learning package by fixing bugs and improving the handling of actions within the environment. They addressed issues related to dummy actions, especially for continuous and interval action spaces, and made necessary adjustments to how these actions are selected and processed. The user also fixed a warning related to keyword arguments and removed an unneeded method from the Monte Carlo learner, which likely improved the efficiency of the code.
juliareinforcement-learningmachine-learningdeep-reinforcement-learningdeep-q-network
Rustlings fork with collective-score integration. Only use it in my Rust course!
Contributions:29 pushes, 45 branches in 7 months
rust