vwxyzjn / cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
http://docs.cleanrl.dev
Other
5.54k stars 631 forks source link

Add docs for `dqn.py` #157

Closed vwxyzjn closed 2 years ago

vwxyzjn commented 2 years ago

Description

This PR adds documentation for dqn.py and couple documentation fixes for dqn_atari.py

Types of changes

Checklist:

If you are adding new algorithms or your change could result in performance difference, you may need to (re-)run tracked experiments. See https://github.com/vwxyzjn/cleanrl/pull/137 as an example PR.

gitpod-io[bot] commented 2 years ago

vercel[bot] commented 2 years ago

This pull request is being automatically deployed with Vercel (learn more).
To see the status of your deployment, click below or on the icon next to each commit.

🔍 Inspect: https://vercel.com/vwxyzjn/cleanrl/AuRtE9dc44G88RDWW5CapYTxT3Pe
✅ Preview: https://cleanrl-git-dqnpy-docs-addition-vwxyzjn.vercel.app

vwxyzjn commented 2 years ago

This PR is ready for review.

vwxyzjn commented 2 years ago

Additional note: I realized it would be pretty hard to run benchmark experiments based on some master's version. From now on, we should do something like

gh pr checkout 157
poetry install

in the reproducibility instructions.

vwxyzjn commented 2 years ago

Looking good over here too. I noticed there is no dqn_atari.py benchmarks in the docs though. Will it be alright ?

The dqn_atari.py docs are already added from #124.

vwxyzjn commented 2 years ago

Let me know if this addresses your concern :)