RTD3 (Recurrent twin-delayed deep deterministic policy gradient)

It's been a while since I've released a video! I'm pretty busy lately, and my family's having a weird time, so I don't know when the next one will be out.
arxiv.org/pdf/2110.12628.pdf
github.com/zhihanyang2022/off-policy-continuous-control
patreon.com/thinkstr

[@ritvikmath]

This reminds me of the KZbin channel Primer but taken to the next level. Super cool!

[@Thinkstr]

Great to hear from you, Ritvik! Thanks for recommending Primer, it looks REALLY cool

[@revimfadli4666]

Why has this channel not blow up yet(despite better upload schedule than most other AI edutainment KZbinrs)?

[@Thinkstr]

Hey, thanks for watching! I think it might be because my subject-matter sort of changes to whatever I'm interested in at the moment, haha.