p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch

DDPG on MountainCar

gearsuccess opened this issue · 2 comments

gearsuccess commented

Hi p-christ,

Thanks for this amazing contribution. Recently, I tried the implementation of DDPG for MountainCar (with default parameters in results/Mountain_Car.py). However, the results are quite different from the plot in READ.me. Could you plz give me some advices?

Thanks

chrisdcs commented

Same question.

And TD3 results are not different as well.

Ritam-M commented

Indeed. There is a tremendous difference in the results, in PPO as well.