DLR-RM / rl-baselines3-zoo

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
https://rl-baselines3-zoo.readthedocs.io
MIT License
1.9k stars 495 forks source link

[Question] Unnecessary Hyperparameter Values for DQN Cartpole-v1 #380

Open prabhatnagarajan opened 1 year ago

prabhatnagarajan commented 1 year ago

❓ Question

I'm looking at the hyperparameters for DQN for Cartpole here, and am seeing something confusing.

The number of timesteps is set to 50k, but the buffer size is set to 100k. Should the buffer size go to 50k? It shouldn't be a big issue, but it is confusing.

Checklist