RL-Baselines

A repository inspired along the lines of the OpenAI Baselines in julia.

Algorithms supported :

Trust Region Policy Optimization

Proximal Policy Optimization

Tested environments :

CartPole-v0 Pendulum-v0

Instructions To Run

Training

Go to the respective algorithm folder cd src/ppo or cd src/trpo and run :

julia train.jl

Testing

cd src/

julia run.jl

Results