If you have a policy that uses diffusion/flow (e.g.
@svlevine14万 位关注者
153,323 次观看
9 条评论
评论来自 X (Twitter) 上的原帖

@svlevine
DSRL trains an actor and Q-function, treating the diffusion noise as the action space. Because samples from the noise prior map to reasonable actions for the policy, DSRL essentially explores "inside" the set of reasonable pre-trained behaviors, making it extremely efficient.
18 个赞

@svlevine
DSRL learns essentially in real time, with good results in as little as 50 trials (it's so efficient that a person can literally sit in front of the robot and push a button to assign sparse rewards).
27 个赞

@svlevine
This was a really fun collaboration led by @ajwagenmaker Project website with paper: To find out more, check out his thread here:
21 个赞

@ahadj0
would a supervised learning version of this work? where the noise distribution is a parmeter that is also optimized along with policy weights

@ahadj0
how long would it take to get that first sparse reward with this method?

@codewithimanshu
Controlling the noise instead of the action itself is a surprisingly effective approach.

@theinsiderzclub
This is pretty amazing, and the visualization made everything so easy to understand😅

@RanCheng10
Will making the initial noise distribution a learnable parameter reduce randomness and thus make the model more prone to overfitting?

@square26circle
😅🥹