search

dusty-nv / jetson-reinforcement

Deep reinforcement learning GPU libraries for NVIDIA Jetson TX1/TX2 with PyTorch, OpenAI Gym, and Gazebo robotics simulator.
MIT License
880 stars 224 forks source link

Loading Robotic Arm Agent #23

Closed dokeash closed 6 years ago

dokeash commented 6 years ago

Hi Dusty , Thanks for incredible repository. I have trained model for robotic arm in Gazebo simulation. When I am loading that model, I can see all trained weights in place but new loaded model does not produce same successful runs . On some blogs I read that we need to wrap environment and then load model. Any pointers on how should I wrap Gazebo environment.

Thanks in advance.

dokeash commented 6 years ago

Resolved it by doing small change in DRQN definition.