ProMP

ProMP copied to clipboard

Hi, Jonas. Thanks for sharing this great project. I am little confused on why we pickle the environment when creating the process in the `MetaParallelEnvExecutor`: ``` self.ps = [ Process(target=worker,...

0xJchen

I ran ppo_run.py and got a .pkl file for HopperRandParamsEnv, of which the average reward was about 200 But when I ran meta_test.py with ProMP-trained policy, the average reward dropped...

R-Ceph

I see that in `envs`, you have some Sawyer push / sliding tasks. Do you have any experimental results on these? I couldn't find them in your paper.

bhairavmehta95

Hi, Thanks for sharing this repo. The code is awesome. I find that currently this repo only supports MLP. If I would like to use RNN or seq2seq neural network...

linkpark

Bumps [joblib](https://github.com/joblib/joblib) from 0.12.2 to 1.2.0. Changelog Sourced from joblib's changelog. Release 1.2.0 Fix a security issue where eval(pre_dispatch) could potentially run arbitrary code. Now only basic numerics are supported....

dependabot[bot]

Bumps [joblib](https://github.com/joblib/joblib) from 0.12.2 to 1.2.0. Changelog Sourced from joblib's changelog. Release 1.2.0 Fix a security issue where eval(pre_dispatch) could potentially run arbitrary code. Now only basic numerics are supported....

dependabot[bot]

Thank you for your inspirational great work and open sourcing the code. I have a question regarding the walker random environment. The walker can not walk when the reward is...

jonathanbrady88

Thanks for sharing the repo! I was wondering which version of Mujoco envs does the repo use? 131, 150, 200?

SapanaChaudhary