Ruosong Wang

CS PhD Student in CMU.
Interested in reinforcement learning

[Ruosong Wang @RuosongW]

@StormRaiser123 我的理解是在batch size不太大的情况下，大部分时间其实花在把data从显存load到cache上？计算量的增大在data比较少的情况下，对GPU不应该是瓶颈

[Ruosong Wang @RuosongW]

@ericxing Congrats!

[Russ Salakhutdinov @rsalakhu]

Is a good representation sufficient for sample-efficient offline RL? In practice, offline RL can be very sensitive to distribution shift even when using features from pretrained neural networks on the same task

https://t.co/K9EKooKT8w

w/t @RuosongW, Wu & @ShamKakade6 #icml2021

[Ruosong Wang @RuosongW]

@StormRaiser123 哥你删除一下

[Ruosong Wang @RuosongW]

@rl_agent Congrats!

[Csaba Szepesvari @CsabaSzepesvari]

More bad news from those mean theoreticians: Unlike in planning with a simulator, even a positive action gap is insufficient for efficient online RL if all one has is linear q^* realizability. Yuanhao Wang's talk is next Tuesday at the RL Theory Seminar. https://t.co/Ct4jYY1d25

[RL Theory Virtual Seminars @RLtheory]

Our next talk:
06/08: Yuanhao Wang (Princeton, @yuanhaowang3)
"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap"

For details, please see the website:
https://t.co/zra0wITmwb

[Ruosong Wang @RuosongW]

@SimonShaoleiDu @StormRaiser123 That's you

[Ruosong Wang @RuosongW]

@StormRaiser123 @zhiyuanli_

[Ruosong Wang @RuosongW]

@StormRaiser123 https://t.co/O0RBD26IZv 这里证明了gd+wd 对带normalization的网络来说等价于gd+exp lr 所以用了normalization之后wd是非常重要的啊

[Ruosong Wang @RuosongW]

@StormRaiser123 这种事情在twitter上说真的好吗

[Ruosong Wang @RuosongW]

@StormRaiser123 为啥要有压力？自己开心就好吧

[RL Theory Virtual Seminars @RLtheory]

Our next talk:
03/09: Ruosong Wang (CMU)
"What are the statistical limits of offline RL with linear function approximation?"

For details, please see the website:
https://t.co/zra0wITmwb

[Noam Brown @polynoamial]

Advisor abuse of power is a serious problem in academia. I know victims who are reluctant to discuss it for fear of damaging their careers, especially if they are on a visa. I'm really happy to see this MIT org pushing to do something about it. Hopefully others follow.

[John Langford @JohnCLangford]

Alekh Agarwal, Akshay Krishnamurthy, and I finished a major tutorial on "Theoretical Foundations of Reinforcement Learning" (https://t.co/hgvm9zALw5) for FOCS (https://t.co/KAen7kXhhA), but potentially of much broader interest. We'll be doing Q&A Friday.

[Ruosong Wang @RuosongW]

@nanjiang_cs Check this https://t.co/QOYNkKw0wx

[Russ Salakhutdinov @rsalakhu]

Planning with Submodular Objective Functions: Instead of maximizing cumulative reward, maximize the objective induced by submodular function. Standard planning & submodular maximization can be viewed as special cases

https://t.co/yLgz1sMHqI

w/ @RuosongW, Zhang, @dchaplot et al

[Ruosong Wang @RuosongW]

This looks impressive

[Pierre Foret @Foret_p]

Introducing SAM: An easy-to-use algorithm derived by connecting PAC Bayesian bounds and geometry of the loss landscape. Achieves SOTA on benchmark image tasks (0.3% error on CIFAR10, 3.9% on CIFAR100) and drastically improves label noise robustness.

https://t.co/aONWVTPZsT

[Duke CompSci @dukecompsci]

Duke Comp Sci PhD candidate Hanrui Zhang receives best student paper award at 28th European Symposium on Algorithms (ESA) Sept. 7-9, 2020. A 4th-yr PhD student, Zhang's research area is Econ. & Computation; he's advised by Prof. Vincent Conitzer. Congrats! https://t.co/e55vvMdo1N