andyzeng / visual-pushing-grasping

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
http://vpg.cs.princeton.edu/
BSD 2-Clause "Simplified" License
898 stars 315 forks source link

Always pushing everything out of view #16

Closed WwYyFan closed 5 years ago

WwYyFan commented 5 years ago

@andyzeng Hi,I use the following command to train a regular VPG policy from scratch in simulation.Have been trained for about six hours, but it always pushing everything out of view.Did I use the wrong training command?

python main.py --is_sim --method 'reactive' --experience_replay --save_visualizations