Closed FabianSchuetze closed 4 years ago
Hello,
You will need to change the Lunar Lander environment. I think you should take a look at: https://github.com/hill-a/stable-baselines/issues/915 You can also look at our tutorial on custom gym environements (cf doc)
Great - thank you very much for your kind and informative reply!
First: This is a wonderful and very instructive repo - thank you very much for creating it!
I would like to train a pixel-based policy for the LunarLander environment. How could this be done? I tried to specify the hyperparameters for the ppo algorithm in the file
hyperparameters/ppo.yml
as follows:When trying to start training the model with
python train.py --algo ppo --env LunarLander-v2
I receive an assertion error:Can somebody kindly illustrate how to use a CNN as feature extractor in this case? I queried
python train --help
but didn't found any indication how I can render the environment and use the resulting images as state.