Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

how to run more episodes? #56

Open
SHITIANYU-hue opened this issue Nov 16, 2020 · 1 comment
Open

how to run more episodes? #56

SHITIANYU-hue opened this issue Nov 16, 2020 · 1 comment

Comments

@SHITIANYU-hue
Copy link

in this script:
https://colab.research.google.com/github/eleurent/highway-env/blob/master/scripts/highway_planning.ipynb

The code only runs one episode, how could I run more episodes to update the agent, and save the model?

@eleurent
Copy link
Owner

This agent is a planning algorithm (Monte-Carlo Tree Search), not a reinforcement learning algorithm : it samples transitions from a known dynamics to find an optimal trajectory starting from the current state. Thus, there is nothing to update and save.

It could be used in a model-based RL fashion, where a model of the dynamics is learned from observed transitions, and then this model is used for planning, as in this script. But it is quite a different goal, and it's not implemented at the moment.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants