-
Hello!
When I run this command: **mpirun -np 2 python -m baselines.run --num_env=1 --alg=her --enFetchPickAndPlace-v1 --num_timesteps=2.5e6 --n_cycles=1**
, it showed up all the traceback as above. …
-
As we can see in the [fetch_env ](https://github.com/openai/gym/blob/924d1349398fa7d0a1ec2a8d5e316aef296115c2/gym/envs/robotics/fetch_env.py#L179-L180)file, there have any definition about the robot g…
-
I cloned the repo, setup the environment and ran (made no changes)
`python her_sac_gym_fetch_reach.py`
The results don't seem to match with [this](https://github.com/vitchyr/rlkit/blob/master/do…
-
I am trying to learn how to run the baseline for the Fetch robot environment. But, when I run the code:
`python -m baselines.run --alg=ppo2 --env=FetchPickAndPlace-v1 --num_timesteps=30000 --nsteps=…
-
No clue if this belongs here but... I've tried modifying the `FetchPickAndPlace-v1` OpenAI environment to replace the cube with a pair of scissors. Everything works perfectly except for the fact that …
-
May I ask why the train success rate for FetchPickAndPlace-v1 is only 0.5 while test success rate is very high?
-
It seems like baselines is not directly implemented to deal with `Box()` type action spaces. This same exact code works for the `CartPole` environment. It fails on `FetchReach-v1`. Here is the code…