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

Here it creates InvertedDoublePendulum using gym. And uses a PPO with 1M steps.


AverageDiscountedReturn: 500 RiseTime: itr 40

ppo_pendulum(ctxt=None, seed=1)

Train PPO with InvertedDoublePendulum-v2 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.