curl icon indicating copy to clipboard operation
curl copied to clipboard

CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

Results 12 curl issues
Sort by recently updated
recently updated
newest added

Hi, thank you for your code. I'm a little bit confused of the infinit bootstrap in https://github.com/MishaLaskin/curl/blob/8416d6e3869e38ca0e46fcbc54a2f784dc09d7fc/train.py#L269 . Will it be wrong when sampling at the end of an episode...

FileNotFoundError: [Errno 2] No such file or directory: './tmp/cartpole/cartpole-swingup-06-22-im84-b128-s202969-pixel/args.json'

Thanks for sharing your code, it's great to be able to go through the implementation. Maybe I'm misunderstanding this, but it seem that if you intend `self.cpc_optimizer` to only optimise...

Hi, can we integrate the update_critic function and update_cpc function by adding the critic_loss and cpc_loss together? Meanwhile, we only need two optimizers. Is it feasible? self.cpc_optimizer = torch.optim.Adam([self.CURL.W], lr=encoder_lr)...

Hi, thanks for sharing your code. I want to ask what is the configuration of the machine on which the code is running

Hi, thank you for sharing your code. When I run run.sh in a ubuntu server, I got a error: > warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow')) CRITICAL:absl:OpenGL version 1.5 or...

Hi, thank you for your great research! I'm afraid I think there is a bug at the random_crop function in utils.py: https://github.com/MishaLaskin/curl/blob/23b0880708c29b078b0a25e62ff31fb587587b18/utils.py#L244-L245 I think the `crop_max` should be modified as...

I'm looking into the code and find that in `def update_cpc()` both `self.encoder_optimizer.step()` and `self.cpc_optimizer.step()` are called. However the parameters of `critic.encoder` are carried by both optimizer. Isn't it true...

I understand that the response might be delayed, but I'm having difficulty locating the MoCo implementation in the CURL codebase. Could you kindly point me to the relevant section or...