josiahls

@ejguan I think you understand what im trying to do. I did go ahead and implemented a practical example that ill attach below. Does this DataPipe accept an argument of...

@ejguan I'm happy to! I'll try to get a pr made later this week hopefully

- [ ] Additional Idea related to the issue of a single env training model. Some models might allow for envs running at the same time. This might make more...

Hi! Version 2 is being developed at https://github.com/josiahls/fast-reinforcement-learning-2, similar to how fastai is developing fastai2 in a different repo. I haven't uploaded a pip package quite yet / could do...

I agree in the limitations of python, Definitely do what you think is best for your goals. At least for fastai, they seem to be looking at swift as a...

Sorry for the late response. I agree! I like their brain first, theory based approach! It's definitely cool that you have worked for a while in the area of concepts,...

Hi, I hope your research is going well! I am just adding a courtesy update here: I recently added DIAYN HRL. I plan to add DADS, then I am going...

Is this still being worked on? I am getting this error below from running the cartpole test. As you can see, the hyperparameters dict has 2 parent keys: Actor, Critic....

Getting a parallel issue with debugging via vscode. I get `personality set failed: Operation not permitted.` It does corectly detect the debugger since I see "Welcome to Mojo debugging" but...

Similar related issue: - Trying to upload coco2017 as a single task - UI loading is very slow. I'm worried about the speed when I have datasets with 1+ million...