Bart/bullet3
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

make sure that the pre-trained galloping and trotting policies work for the minitaur_reactive_env and minitaur_trotting_env environments.

Browse Source
This commit is contained in:
Jie
2018-04-24 21:48:27 -07:00
parent 982453abc6
commit a375a349ce
43 changed files with 4447 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/pybullet/gym/pybullet_envs/minitaur/envs/README Normal file
View File

@@ -0,0 +1,11 @@
This folder contains a number of simulated Minitaur environments implemented using pybullet.
The following two environments are used in the RSS paper "Sim-to-Real: Learning Agile Locomotion For Quadruped Robots":
1) Galloping example: minitaur_reactive_env.py
python minitaur_reactive_env_example.py runs a pre-trained PPO agent that performs galloping gait.
2) Trotting example: minitaur_trotting_env.py
python minitaur_trotting_env_example.py runs a pre-trained PPO agent that performs trotting gait.
The rest are experimental environments.