search

wisnunugroho21 / reinforcement_learning_ppo_rnd

Deep Reinforcement Learning by using Proximal Policy Optimization and Random Network Distillation in Tensorflow 2 and Pytorch with some explanation
GNU General Public License v3.0
47 stars 5 forks source link

if i want employe this work to a new env, what should i do？ #9

Open SOMEAIDI opened 3 years ago

SOMEAIDI commented 3 years ago

Tanks for the great work! I'd like to konw if i want employe ppo_rnd on the new continuous env which is created by myself, what should i do?Do you have any suggests?

wisnunugroho21 commented 3 years ago

Sorry if I'm so late to reply.

You can create your own env class which implements the reset function and the step function. The reset function must return initial state. The step function must accept action & return observation, reward, done, info.

Then in line 374, change the code to call your env class