-
When I use parallel='process', the tf.summary.scalar call in the summarize_episode function doesn't return. If I use 'thread' or 'none' the tf.summary.scalar function finishes normally. I have no idea…
-
Hi, I am using jaco for reinforcement in RLBench. I tried the RLBench/examples/single_task_rl.py and I have two questions:
1. How to set jaco arm correctly?
At first, I just set like this:
`env …
-
In RLBench_env.py, step() function should return {} instead of None
-
Hi, I was running the imitation learning code to get the velocities of the joints.
```
from rlbench.environment import Environment
from rlbench.action_modes import ArmActionMode, ActionMode
from…
-
Hello, I want to run the environment on my local computer (windows10,python==3.6);
Here are my steps:
1. Since the raw code runs on Linux, to switch to windows, I change the _remoteApi_.so to _remo…
-
What's the supported way to edit environments (the task ttms) programmatically?
-
Setting action_mode = ActionMode(ArmActionMode.DELTA_EE_POSE) for the gym reach_target task, for example, gives rlbench.task_environment.InvalidActionError: Could not find a path. This is due to the a…
-
For the imitation learning example script, is it possible to send the predicted actions to the scene instead of just computing the loss?
By this I mean, can I test the robot with my networks' predi…
-
Hi, Awesome framework :)! It would be great if you can clarify some points about the simulator.
- In the complex task tutorial, it is mentioned that "As previously mentioned, the physics engine ru…
-
When I create a Vision sensor in the environment, even if I don't invoke capture_rgb(), the task steps become dramatically slower. Using cProfile shows some of the calls taking .17s and the others tak…