Stable-Baselines-Team / stable-baselines3-contrib

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
https://sb3-contrib.readthedocs.io
MIT License
465 stars 173 forks source link

Fix `train_freq` type annotation for TQC and QR-DQN #229

Closed Armandpl closed 8 months ago

Armandpl commented 8 months ago

Description

Allow a tuple (e.g (5, "step") or (2, "episode")) to be passed as the train_freq argument, as per the documentation, for TQC and QR-DQN.

Context

closes #228

Types of changes

Checklist:

Note: we are using a maximum length of 127 characters per line