reps_gym_cartpole

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

Here it runs gym CartPole env with 100 iterations.

Results:

AverageReturn: 100 +/- 40 RiseTime: itr 10 +/- 5

reps_gym_cartpole(ctxt=None, seed=1)

Train REPS with CartPole-v0 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.