This is an example to train Task Embedding PPO with PointEnv.

te_ppo_mt10(ctxt, seed, n_epochs, batch_size_per_task, n_tasks)

Train Task Embedding PPO with PointEnv.

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

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

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

  • batch_size_per_task (int) – Batch size of samples for each task.

  • n_tasks (int) – Number of tasks to use. Should be a multiple of 10.