Experiments on MuJoCo tasks

The Swimmer task is a good example to test TRPO. This task involves a 3-link swimming robot in a viscous fluid, where the goal is to make it swim forward as fast as possible by actuating the two joints (http://gym.openai.com/envs/Swimmer-v2/). The following screenshot shows how Swimmer looks in the MuJoCo simulator:

To train an agent for Swimmer, run the following command under the src folder:

CUDA_VISIBLE_DEVICES= python train.py -t Swimmer

There are two arguments in train.py. One is -t, or --task, indicating the name of the MuJoCo or classic control task you want to test. Since the state spaces of these control ...

Get Python Reinforcement Learning Projects now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.