How can I quickly reference your policy in a new scenario?

[li200005]

How can I quickly implement your policy in a new scenario? I am looking to apply your policy in a new scenario, but I noticed that your code loads a pre-trained reinforcement learning model. How can I rapidly train a model that matches your policy in a new environment? For instance, how can I train a model that can be directly used with your ppo_inference_tf function?