te_ppo_point
¶
This is an example to train Task Embedding PPO with PointEnv.
- circle(r, n)¶
Generate n points on a circle of radius r.
- N = 4¶
- goals¶
- TASKS¶
- te_ppo_pointenv(ctxt, seed, n_epochs, batch_size_per_task)¶
Train Task Embedding PPO with PointEnv.
- Parameters
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.
n_epochs (int) – Total number of epochs for training.
batch_size_per_task (int) – Batch size of samples for each task.