te_ppo_metaworld_mt1_push
¶
This is an example to train Task Embedding PPO with PointEnv.
- te_ppo_mt1_push(ctxt, seed, n_epochs, batch_size_per_task)¶
Train Task Embedding PPO with PointEnv.
- Parameters
ctxt (ExperimentContext) – The experiment configuration used by
Trainer
to create theSnapshotter
.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.