Yang Yue

reproduce the result of CrazyClimber

13

The paper show three runnings of CrazyClimber as below. It seems stable and of high performance.   However, when I rerun the code three times using the given command....

see https://github.com/astooke/rlpyt/blob/f04f23db1eb7b5915d88401fca67869968a07a37/rlpyt/agents/dqn/dqn_agent.py#L29 The predicted q value and target q value are calculated on GPU and then be put on cpu. Consequently, the dqn loss is calculated on cpu. I'm confused...

Questions about validation set

2

hi @mees , thanks for your great work! I notice in each scene, there are separate training and validation set. I have some questions: 1. What are the validation data...

Visualization Tool

2

@ChathuraT @Cheng-Xue @Vimukthini , Thanks for great work of you guys! I recently work on evaluating visual agent physical intelligence and found the repo very useful. However, when i wanna...