garage
garage copied to clipboard
A toolkit for reproducible reinforcement learning research.
Fix #2079
The first draft of PCGrad with tf. The optimizer is from the author (https://github.com/tianheyu927/PCGrad). Do the following things to use the optimizer. - Input a list of losses Tensor to...
Readme and template for documenting how to create a new CI file for releases. Right now the process must be done manually.
I want to visualize the arm movement during training, but I'm not sure how to visualize the mujoco environment. I've called the function: env.visualize(),but it doesn't works. Can someone help...
When I try the example garage/examples/torch/mtsac_metaworld_mt1_pick_place.py , and it works. But when I change the plot atrr to True . it showed that : ![image](https://user-images.githubusercontent.com/18379106/118622751-30996b80-b7fa-11eb-8669-7dac08fa6f91.png) ![image](https://user-images.githubusercontent.com/18379106/118622834-41e27800-b7fa-11eb-926c-22a7216a3787.png) Thanks!
Hi there, I am currently on the `master` branch, I test `maml_trpo` and `trpo` on garage env `PointEnv` to see if `maml_trpo` works better than `trpo`, but I found the...