Branch: master
Find file History
pzhokhov mpi-less baselines (#689)
* make baselines run without mpi wip

* squash-merged latest master

* further removing MPI references where unnecessary

* more MPI removal

* syntax and flake8

* MpiAdam becomes regular Adam if Mpi not present

* autopep8

* add assertion to test in mpi_adam; fix trpo_mpi failure without MPI on cartpole

* mpiless ddpg
Latest commit ab59de6 Oct 31, 2018
Permalink
Type Name Latest commit message Commit time
..
Failed to load latest commit information.
README.md update readmes (#514) Aug 16, 2018
__init__.py add __init__.py Aug 28, 2017
defaults.py tighten flake8, autopep8 to fix trailing whitespaces and blank lines … Sep 11, 2018
trpo_mpi.py mpi-less baselines (#689) Oct 31, 2018

README.md

trpo_mpi

  • Original paper: https://arxiv.org/abs/1502.05477
  • Baselines blog post https://blog.openai.com/openai-baselines-ppo/
  • mpirun -np 16 python -m baselines.run --alg=trpo_mpi --env=PongNoFrameskip-v4 runs the algorithm for 40M frames = 10M timesteps on an Atari Pong. See help (-h) for more options.
  • python -m baselines.run --alg=trpo_mpi --env=Ant-v2 --num_timesteps=1e6 runs the algorithm for 1M timesteps on a Mujoco Ant environment.
  • also refer to the repo-wide README.md