TecNets

TecNets copied to clipboard

Hi! I have noticed that during training the control network has to predict only one action per episode (one from a query demo and one from a support demo so...

telejesus2

Issues running the experiments

2

Hi Stephen, I'm running into a few issues trying to run the experiments: * AttributeError: 'ReacherMILEnv' object has no attribute 'set_visibility' > I had to comment out a couple of...

nimaasg

AttributeError: 'ReacherMILEnv' object has no attribute 'viewer'

3

When I run ./tecnets_corl_results.sh sim_reach,error appear： Traceback (most recent call last): File "/home/user/gym-mil/gym/core.py", line 203, in del self.close() File "/home/user/gym-mil/gym/core.py", line 164, in close self.render(close=True) File "/home/user/gym-mil/gym/core.py", line 150, in...

HongminWu

I found this paper used RLbench to do a good simulation which can transfer to real robot successfully. It can be a good example to learn how to use Rlbench,...

superggb