RLBench
RLBench copied to clipboard
A large-scale benchmark and learning environment.
Hello!, like you said in the swapping arms section: "Don't see the arm that you want to use? Your first step is to make sure it is in PyRep, and...
I am getting this issue when running examples in `RLBench/examples/rlbench_gym.py` `QXcbIntegration: Cannot create platform OpenGL context, neither GLX nor EGL are enabled terminate called after throwing an instance of 'std::logic_error'...
Hello, I'm Yuya, a first-year graduate student from Japan. I'm interested in applying reinforcement learning to robots. I'm trying to understand RLBench. I've read the paper. I would like to...
Hi, I believe the issue I'm facing is somewhat similiar to issue #146. I'm using Ubuntu 20.04 from WSL in Windows and CoppeliaSim 4.1. I'm able to run the examples...
Dear developer, right now I am working with RLBench as a framework to collect demonstrations for a DRL-algortihm. Instead of going straight from waypoint to waypoint I am using a...
Hi! I'm trying to get the positions of the objects of my scene to calculate the distance between the robot Gripper and the Red Ball that I need to catch...
Hi, thanks for maintaining this amazing project! I have question for solving ik via Jacobian that is conducted via rlbench API. in [this line of code](https://github.com/stepjam/RLBench/blob/31c7bd96df1cdc06959d2c33f5751e5539925b27/rlbench/backend/scene.py#L155) we disable dynamics for...
Hi Stephen, I have added my custom robot, (Wendy), PyRep by following the tutorial. The first picture shown is running the unit test, which shows a warning but at the...
Thanks for this amazing tool :) I've tried to execute [examples/swap_arm.py](https://github.com/stepjam/RLBench/blob/master/examples/swap_arm.py) with `jaco` instead. ```python3 env = Environment( action_mode, obs_config=obs_config, headless=False, robot_setup='jaco') ``` However, when the CoppeliaSim windows popped up,...
Hi, I have a question regarding the implementation of dense reward signal. I was able to implement the reward signal but my test results always lead to the arm curling...