rl2_ppo_halfcheetah

Example script to run RL2 in HalfCheetah.

rl2_ppo_halfcheetah(ctxt, seed, max_episode_length, meta_batch_size, n_epochs, episode_per_task)

Train PPO with HalfCheetah environment.

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

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

  • max_episode_length (int) – Maximum length of a single episode.

  • meta_batch_size (int) – Meta batch size.

  • n_epochs (int) – Total number of epochs for training.

  • episode_per_task (int) – Number of training episode per task.