search

Xingyu-Lin / mbpo_pytorch

A pytorch reprelication of the model-based reinforcement learning algorithm MBPO
150 stars 38 forks source link

Epoch length? #3

Open xfdywy opened 3 years ago

xfdywy commented 3 years ago

Hi,

Thank you for your code. It is really helpful.

Could you please check the line 115 in the main_mbpo.py? Since start_step will become larger and larger, if the condition is cur_step >= start_step + epoch_length, the truth epoch_length will also become larger and larger. So, is it a bug? Should we use

cur_step >= args.epoch_length？

Correct me if I am wrong.

Thanks

https://github.com/Xingyu-Lin/mbpo_pytorch/blob/43c8a55fa7353c6aed97525d0ecd5cb903b55377/main_mbpo.py#L115

` cur_step = total_step - start_step

        if cur_step >= start_step + args.epoch_length and len(env_pool) > args.min_pool_size:
            break

`

mickelliu commented 3 years ago

I have the same question. Does not make sense to me.

945716994 commented 2 years ago

I think this may instead by cur_step >= args.epoch_legnth ....