search

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

PyTorch implementations of deep reinforcement learning algorithms and environments
MIT License
5.55k stars 1.19k forks source link

DDPG on MountainCar #38

Open gearsuccess opened 4 years ago

gearsuccess commented 4 years ago

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 4 years ago

Same question.

And TD3 results are not different as well.

Ritam-M commented 3 years ago

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