dodox/mujoco_maze
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
fork of https://github.com/kngwyu/mujoco-maze with some fixes
26 Commits 1 Branch 0 Tags 898 KiB
Python 100%
767bd1891a
Go to file
kngwyu 767bd1891a Fix format specifier
2020-06-28 18:46:09 +09:00
mujoco_maze Fix format specifier 2020-06-28 18:46:09 +09:00
tests More precise obs space for point mazes 2020-06-24 22:42:52 +09:00
.gitignore INITIAL 2020-05-21 19:05:06 +09:00
LICENSE INITIAL 2020-05-21 19:05:06 +09:00
poetry.lock Make it work 2020-05-25 17:26:57 +09:00
pyproject.toml Introduce MazeCell and refactor 2020-06-04 14:31:00 +09:00
README.md Update README 2020-06-04 14:34:00 +09:00
setup.cfg INITIAL 2020-05-21 19:05:06 +09:00
setup.py Use self.sim instead of physics 2020-05-29 17:04:26 +09:00

README.md

mujoco-maze

Some maze environments for reinforcement learning(RL) using mujoco-py and openai gym.

Thankfully, this project is based on the code from rllab and tensorflow/models.

Implemeted Environments

  • Distance based rewards

    • AntMaze-v0
    • AntPush-v0
    • AntFall-v0
    • PointMaze-v0
    • PointPush-v0
    • PointFall-v0

  • Goal rewards + step penalty

    • AntMaze-v1
    • AntPush-v1
    • AntFall-v1
    • PointMaze-v1
    • PointPush-v1
    • PointFall-v1

License

This project is licensed under Apache License, Version 2.0 (LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0).