A problem in Chapter 5: DDPG

sweetice / Deep-reinforcement-learning-with-pytorch

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

MIT License

3.75k stars 837 forks source link

A problem in Chapter 5: DDPG #17

Open MoonieC opened 4 years ago

MoonieC commented 4 years ago

I don't konw if it's because of my device or the program, but this pendulum-v0 just doesn't work so well in my device. You see, the pendulum only moves one circle and for some reason, it just stops moving! I tried multiple ways and haven't figured out why? Hopefully you might tell me what is going wrong?

lbq8942 commented 2 years ago

i think the author has already run away

ohhorange commented 11 months ago

I encounter this error as well，the error message denote that the pendulum-v0 has been aborted, try to use the pendulem-v1, and it work.