Skip to content
No description, website, or topics provided.
Branch: master
Clone or download
Latest commit 4d55f96 Jul 21, 2017
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
contrib sync rllab++ Jul 21, 2017
docker initial commits Jan 8, 2017
docs sync rllab++ Jul 21, 2017
examples sync rllab++ Jul 21, 2017
rllab sync rllab++ Jul 21, 2017
sandbox sync rllab++ Jul 21, 2017
scripts
tests sync rllab++ Jul 21, 2017
vendor/mujoco_models sync rllab++ Jul 21, 2017
CHANGELOG.md initial commits Jan 8, 2017
LICENSE initial commits Jan 8, 2017
README.md sync rllab++ Jul 21, 2017
README.md.orig initial commits Jan 8, 2017
circle.yml initial commits Jan 8, 2017
environment.yml sync rllab++ Jul 21, 2017
setup.py initial commits Jan 8, 2017

README.md

rllab++

rllab++ is a framework for developing and evaluating reinforcement learning algorithms, built on rllab. It has the following implementations besides the ones implemented in rllab:

The codes are experimental, and may require tuning or modifications to reach the best reported performances.

Installation

Please follow the basic installation instructions in rllab documentation.

Examples

From the launchers directory, run the following, with optional additional flags defined in launcher_utils.py:

python algo_gym_stub.py --exp=<exp_name> 

Flags include:

The experiment will be saved in /data/local/<exp_name>.

Citations

If you use rllab++ for academic research, you are highly encouraged to cite the following papers:

You can’t perform that action at this time.