First algorithm will be DDPG working on an "inverted pendulum" environment.
DanielLSM/Gazebo-DRL
Deep Reinforcement Learning on simple Gazebo worlds. Wrapped in a "gym like" manner, inspired on the gym-gazebo branch.
Python
Deep Reinforcement Learning on simple Gazebo worlds. Wrapped in a "gym like" manner, inspired on the gym-gazebo branch.
Python