This is an example to train TRPO on MT50 environment.
- mttrpo_metaworld_mt50(ctxt, seed, epochs, batch_size, n_workers, n_tasks)¶
Set up environment and algorithm and run the task.
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.
epochs (int) – Number of training epochs.
batch_size (int) – Number of environment steps in one batch.
n_workers (int) – The number of workers the sampler should use.
n_tasks (int) – Number of tasks to use. Should be a multiple of 50.