Mirko Morati comments

Repositories
Issues
Comments

Results 2 comments of


                                            Mirko Morati

Results using RLBench as the environment

I have a similar problem using the CPU and around the 7th episode.

Results using RLBench as the environment

I'm testing the `ReachTarget` task using the `DDPG` algorithm. Also I'm using the `vision` state type. Using only the robot state doesn't produce any performance drop. Also I have tensorflow-gpu==2.1.0...