This is a Pytorch implementation of the 'TD3PG' paper (Both of the jupyter notebook and python script is used for the 'main' file and for several others too)
Paper: Addressing Function Approximation Error in Actor-Critic Methods
Down below are the graphical results on some of the 'mujoco' and 'box2d' environments of this implementation. Several other environments are also to be solved and added.
To check out the 'open ai gym leaderboard' here is the link
Note: In the title of the plot there should be '1000 scores' instead of '100 scores'
