This is an example to train a task with TRPO algorithm.

Here it runs CartPoleBulletEnv environment with 100 iterations.

trpo_cartpole_bullet(ctxt=None, seed=1)

Train TRPO with Pybullet’s CartPoleBulletEnv environment.

  • ctxt (garage.experiment.ExperimentContext) – The experiment configuration used by Trainer to create the snapshotter.

  • seed (int) – Used to seed the random number generator to produce determinism.