rl2_ppo_metaworld_ml1_push

Example script to run RL2 in ML1.

rl2_ppo_metaworld_ml1_push(ctxt, seed, meta_batch_size, n_epochs, episode_per_task)

Train RL2 PPO with ML1 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.

  • 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.