-
Mujoco control tasks
The authors used the Mujoco control tasks, including Ant-v2, HalfCheetah-v2, Hopper-v2, and Walker2d-v2. -
Desk Cleanup environment
The Desk Cleanup environment, which consists of a robotic arm and several blocks on a desk. -
Fetch Manipulation environment with 3 blocks
The Fetch Manipulation environment with 3 blocks, which consists of a robotic arm with a gripper and three blocks. -
Fetch Manipulation environment with 2 blocks
The Fetch Manipulation environment with 2 blocks, which consists of a robotic arm with a gripper and two blocks. -
Fetch Manipulation environment
The Fetch Manipulation environment built on top of Mujoco, which consists of a robotic arm with a gripper and square blocks. -
Mujoco Benchmarking Continuous Control Tasks
The dataset used in the paper is the Mujoco benchmarking continuous control tasks. -
Mujoco tasks
The dataset used in the paper is not explicitly described, but it is mentioned that it is a collection of expert demonstrations for imitation learning tasks.
