garage
garage copied to clipboard
A toolkit for reproducible reinforcement learning research.
With [#1845 ](https://github.com/rlworkgroup/garage/pull/1845), we support returning episode_info from an environment at `reset()`. We should put `active_task_one_hot` in `MultiEnvWrapper`'s episode_info.
With [#1845 ](https://github.com/rlworkgroup/garage/pull/1845), we can delete `DmControlViewer` and use https://github.com/deepmind/dm_control/tree/master/dm_control/viewer
When running the sac example with the plotter enabled, the plotter crashes.
Hi, I would like to use an array of integers as action of my custom environment. For example, I want my action to be like [1 2 4]. I'm using...
In line 86 ([torch/_functions.py](https://github.com/rlworkgroup/garage/blob/f856f74eacb0d8f535eb36d9c84309efbc25c384/src/garage/torch/_functions.py#L86)), a runtime error is thrown when the rewards/baselines and filters are located on different devices. I suggest to either introduce an optional parameter `device` or querying...
I have an open PR and the CI check is unable to build the docker container. It fails with: ![Screenshot from 2020-11-05 15-14-49](https://user-images.githubusercontent.com/44059971/98239381-f1e84600-1f78-11eb-8dd0-7118473791f5.png) I haven't changed any setup files on...