Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

SubprocVecEnv does not support rendering #206

Open
timmeinhardt opened this issue Nov 15, 2017 · 1 comment
Open

SubprocVecEnv does not support rendering #206

timmeinhardt opened this issue Nov 15, 2017 · 1 comment

Comments

@timmeinhardt
Copy link

Why does the SubprocVecEnv class and the corresponding worker wrapper function not support calling the render method of an environment?

@jlabhishek
Copy link

Did anyone find a way to do so?

AdamGleave pushed a commit to HumanCompatibleAI/baselines that referenced this issue Apr 5, 2019
* Remove GAIL results

* Begin GAIL cleanup

* Fixes for GAIL + add tests

* Fix GAIL saving/loading

* Add notes

* Bug fixes + update changelog for GAIL

* Remove unused file

* Fix A2C with continuous actions
+ update logging

* Fix ACKTR runner

* Fixed behavior cloning + add test

* Add pretrain method

* Update coverage rc

* Rename dataset file

* Refactor expert dataset generation

* Clean up code for codacy

* Remove unused import

* Fix close method for DummyVecEnv

* Add support for pretraining with discrete actions

* Style fix

* Kill env processes to avoid memory error during tests

* Call close instead of killing processes

* Start rewriting expert dataset
In order to support image dataset

* Style fixes

* Add image dataset recorder

* Add documentation for pretraing + GAIL

* Remove pretrain with image buggy test for now

* Fix forkserver hanging when using atari env

* Reduce number of cpu for atari envs

* Change default start method (test CI)

* Test sequential mode

* Add sequential processing param

* Switch back to fork start method + add warning

* Add discrete actions support for GAIL + fix deprecations

* Update documentation

* Clean up + format code

* Replace num_iters by n_epochs + update doc

* Do not display NaN reward when not using Monitor (for SAC)

* Document Gumbel-max trick

* Simplify dataloader

* Expert model can be a callable
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants