Edan Toledo

Results 11 comments of Edan Toledo

@arnupretorius - Adding the option for a single optimizer is easy and I will do it now but from a design standpoint which optimizer should optimize the observation network in...

Both keys returned are brand new keys, it doesn't necessarily matter which one is consumed and which one is kept to create further new keys. I think consistency is nice...

I agree Best Regards, Edan Toledo ________________________________ From: Sasha ***@***.***> Sent: Thursday, July 21, 2022 6:52:16 PM To: instadeepai/Mava ***@***.***> Cc: Edan Toledo ***@***.***>; Assign ***@***.***> Subject: Re: [instadeepai/Mava] Feature/jittable...

For all future visitors to this issue, my solution might not solve your problem but it solves it for me every time: `export LD_PRELOAD=""` I do this before running my...

Yeah, that would work better and thanks ill look into that for my specific use case but I don't think the default behaviour should be the multiple next calls -...

The latter is preferred definitely. I just think it would be useful for quite a few use cases.

I have done this before and can confirm this is possible and can bring speed improvements. It might not be so easy to modify the dreamerv3 open-source codebase but doing...

Hey! Just a heads up, my implementation of MAML was really off the cuff. I haven't thoroughly tested it in any capacity. It was just me trying to do basic...