D4RL
D4RL copied to clipboard
A collection of reference environments for offline reinforcement learning
Hi, thank you very much for providing such a good open source dataset, but I am having the same problem as #98 when running Maze2D and AntMaze on windows. The...
I am getting OSError : Cannot find MuJoCo library /home/noa/.mujoco/lib/libmujoco.so.2.1.1. issue. I successfully installed d4rl with pip install e . but I am getting this error when importing d4rl. The...
when I try to install this, I encounter "ERROR: Command errored out with exit status 128: git clone -q git://github.com/deepmind/dm_control /tmp/pip-install-z7djkhsc/dm-control_750010d3edcd47c991d434681980f049 Check the logs for full command output."
When I just finished installing d4rl, the following error will appear when importing d4rl: "oserror: cannot find mujoco library at / home / NOA /. Mujoco / lib / libmujoco....
Hi, thanks for the contribution. I checked the qlearning_dataset, looks there are two small errors. - The next observations https://github.com/rail-berkeley/d4rl/blob/4aff6f8c46f62f9a57f79caa9287efefa45b6688/d4rl/__init__.py#L105 I think mostly in `qlearning_dataset` it drops the result since...
>>> import d4rl Warning: Flow failed to import. Set the environment variable D4RL_SUPPRESS_IMPORT_ERROR=1 to suppress this message. No module named 'flow' Traceback (most recent call last): File "", line 1,...
I think this is related to this issue https://github.com/openai/gym/issues/2593 I think that the Ant-v2 datasets where collected without contact forces. For example I found no observation with non-zero component between...
git clone https://github.com/rail-berkeley/d4rl.git cd d4rl pip install -e . and then:  I've tried mujoco200 and mujoco210, installing in win10 and ubuntu, the same mistake occured
this exception happened when I tried to run the test code. Why this happened and how to solve it? 
Hi, Thanks for releasing these environments and this data! I'm having some issues recovering the original trajectories from Androit environments in a way that seems to make sense, mainly because...