Alvin Zhang

Results 11 comments of Alvin Zhang

Hi, To support tensorboard in stable-baselines, we need to define a tb log location for the RL agent. In this repo, arguments of the RL agent are defined by the...

@dosovits Hi, thanks for your explanation. I guess you're right. However, the source code is really confusing. According to the source code, there should have subdirectories "bin/python, bin/vizdoom, bin/.." under...

@dosovits Yes, you're right. I do installed the VizDoom toolbox with pip.

@rrahmati Thanks for the reminder. Unfortunately, It doesn't work for this version. I tried other versions like v5.3, v5.7 and all failed. Is it possible that an older version lower...

> Hi, thank you very much for your suggestion. But when I compare the code you gave, it looks like you just removed the parentheses, but in fact their operations...

Hi @atenpas , I fixed this by initializing all boost::array object with command `boost:array object = {{ }}`, i.e. using double brace.

@JamesChuanggg A distribution should retrieve a value between 0 and 1. Log of that value should always be negative. How could you get a positive value from `self.normal_dist.log_prob( )` method?...

> @huiwenzhang Not such issue has been reported before. Maybe you could check whether your pytorch and CUDA version are compatible. Sometimes that could have an effect on the memory...

> Thanks for your contribution, can I see the lined rgb image by changing the debug parameter when running run_linemod.py This is how I visualize the linemod, modify the function...

> @TechyRio The data format is exactly as you pasted above according to the code. However, the bigbird dataset format is very different from the format used in this repo....