trpo_swimmer

An example to train a task with TRPO algorithm.

trpo_swimmer(ctxt=None, seed=1, batch_size=4000)

Train TRPO with Swimmer-v2 environment.

Parameters

• 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.

• batch_size (int) – Number of timesteps to use in each training step.