Call ppo2 and not ppo1

This commit is contained in:
definitelyuncertain
2017-12-02 22:00:28 +05:30
committed by GitHub
parent b05be68c55
commit 643184935e

View File

@@ -2,5 +2,5 @@
- Original paper: https://arxiv.org/abs/1707.06347
- Baselines blog post: https://blog.openai.com/openai-baselines-ppo/
- `mpirun -np 8 python -m baselines.ppo1.run_atari` runs the algorithm for 40M frames = 10M timesteps on an Atari game. See help (`-h`) for more options.
- `python -m baselines.ppo1.run_mujoco` runs the algorithm for 1M frames on a Mujoco environment.
- `mpirun -np 8 python -m baselines.ppo2.run_atari` runs the algorithm for 40M frames = 10M timesteps on an Atari game. See help (`-h`) for more options.
- `python -m baselines.ppo2.run_mujoco` runs the algorithm for 1M frames on a Mujoco environment.