Skip to content
#

distributional-rl

Here are 22 public repositories matching this topic...

PyTorch implementation of the state-of-the-art distributional reinforcement learning algorithm Fully Parameterized Quantile Function (FQF) and Extensions: N-step Bootstrapping, PER, Noisy Layer, Dueling Networks, and parallelization.

  • Updated Oct 10, 2020
  • Jupyter Notebook

Minimal, deterministic C51 reproduction with n-step returns, Polyak averaging, and Double DQN, benchmarked against a matched DQN baseline. Built for clarity, reproducibility, and controlled ablations over atoms, support bounds, and evaluation protocols, with stable training and plot-ready outputs.

  • Updated Oct 20, 2025
  • Python

Improve this page

Add a description, image, and links to the distributional-rl topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the distributional-rl topic, visit your repo's landing page and select "manage topics."

Learn more