Tutorials: Baselines

[These video tutorials has been depreciated for it being difficult to maintain, please simply follow the instructions/documentations on the Github page which covers everything you need.]

Github: Arena-Baselines

Get Started 1: Setup the Environment [Video contains names, temporally hidden for review policy]

Setup a Python environment for the baselines.

If you are not using a remote machine without X-Server, simply skip the part of setting up X-Server.

Get Started 2: Run Baselines [Video contains names, temporally hidden for review policy]

Run typical baselines.

Get Started 3: Monitor the Training Progress [Video contains names, temporally hidden for review policy]

Use TensorBoard to monitor the training progress.

Visualize Trained Agents

Visualize the trained agents and produce pictures that can be used in a paper.

Common Problems: Game Threads Still Running

Sometimes, the game threads do not exit properly after you kill the python thread.

Common Problems: Port still in use

It takes some time for the port to release after you killed the python thread.

Utils: Copy Models

You may find it is useful to copy models from a remote server to your desktop, so that you can see training visualization of the game.

Check Your Configurations

All configurations are summarized as a markdown table in TensorBoard.

More to come...

Page updated

Google Sites

Report abuse