Mohak Bhardwaj @mostlymohak Twitter profile

Last Seen Profiles

@N0bitexmarket

@mikey_mack14

@elisawrld

@Fooz37202185

@SugarRachel_

@XiLiu82680

@ItalyinEstonia

@Gravie

@Sadik0707

@bokeplokalmalam

@sukabinor2847

@thomastroops

@Suka1iya

@bokeplokalmalam

@NCTsmtown

@stw_pdg

@a0si_a0_

@bokeplokalmalam

@oodnakab

@Furkan1554960

@GlitteranSpice

@OUParking

@ManahelAl_otibi

@nw_min

@youtubeko

@Malchazz

@AkumaTari505

@Malchazz

@shamoons

@urus

@Milo_msbox

@CricAspect

@ZihaoBase

@BinorRaja

@bokeplokalmalam

@VmaniakJ

Mohak Bhardwaj

@mostlymohak

3 months

Slightly belated life update: In April I started as a Research Scientist in the Atlas team at @BostonDynamics . Really excited to continue research in learning and manipulation with this amazing team and our shiny new humanoid!

15

535

Mohak Bhardwaj

@mostlymohak

5 months

Really excited to share that I successfully defended my PhD thesis at @uwcse earlier this month! My deepest gratitude to my committee and everyone who helped me along this 5 year journey!

4

1

41

Mohak Bhardwaj

@mostlymohak

8 months

Full version of our @NeurIPSConf 2023 paper titled Adversarial Model for Offline Reinforcement Learning is now available on arxiv Joint work with @tengyangx , @nanjiang_cs , Byron Boots and @chinganc_rl . Open source code coming soon!

Adversarial Model for Offline Reinforcement Learning

We propose a novel model-based offline Reinforcement Learning (RL) framework, called Adversarial Model for Offline Reinforcement Learning (ARMOR), which can robustly learn policies to improve upon...

arxiv.org

0

8

37

Mohak Bhardwaj

@mostlymohak

7 months

Really excited to share work done during my @GoogleDeepMind internship. We introduce Box o' Flows, a benchtop control system for real-world fluid directed rigid body control and demonstrate how deep RL can be used to learn highly dynamic tasks directly on real hardware.

Markus Wulfmeier

@m_wulfmeier

7 months

Reinforcement learning is most useful if a) demonstrations are hard to get and b) a system is hard to model. ( a) no imitation, b) no MPC etc) Excited to share Mohak's internship report and the 'Box o Flows' enabling us to ask questions in this space!

1

8

51

1

4

22

Mohak Bhardwaj

@mostlymohak

2 months

Come over to the poster session 4 at @l4dc_conf today if you're interested in learning more about our work on controlling a complex fluid dynamical system with RL directly in the real world.

Markus Wulfmeier

@m_wulfmeier

2 months

. @l4dc_conf is happening @UniofOxford this week! Two fantastic papers coming up from our group @GoogleDeepMind in collaboration with @MIT ! First @timseyde continues the path of 'Q-learning is all you need' even for continuous control with 'Growing Q-Networks'

0

7

27

0

1

8

Mohak Bhardwaj

@mostlymohak

4 years

Excited to announce that our paper "Blending MPC and Value Function Approximation for Efficient Reinforcement Learning" recently got accepted to #ICLR2021 ! Thanks to my co-authors Sanjiban Choudhary @sanjibac and Byron Boots for making this work possible.

0

2

5

Mohak Bhardwaj

@mostlymohak

3 years

Really excited to present our paper STORM: An Integrated Framework for Fast Joint Space MPC for Reactive Manipulation at @corl_conf ! Checkout our oral talk on Thurs 10am GMT.

STORM: An Integrated Framework for Fast Joint-Space...

Sampling-based model-predictive control (MPC) is a promising tool for feedback control of robots with complex, non-smooth dynamics, and cost functions. However, the computationally demanding...

arxiv.org

0

2

Mohak Bhardwaj

@mostlymohak

1 month

@hganjoo_153 Congrats bhai!!

0

1

Mohak Bhardwaj

@mostlymohak

3 months

@hganjoo_153 @BostonDynamics Thanks bhai!!

0

1

Mohak Bhardwaj

@mostlymohak

4 years

@airindiain Will more flights be added from Delhi to USA, especially SFO? I have been trying to book from the website for many days but everything is unavailable so far.

0

Mohak Bhardwaj

@mostlymohak

4 years

@therealjsacks3 An invalid assumption in a hypothetical scenario.

0

1

Mohak Bhardwaj

@mostlymohak

7 months

A big thanks to my collaborators Jonas Buchli, Martin Riedmiller, @m_wulfmeier , Thomas Lampe, Michael Neunert, Francesco Romano, Abbas Abdolmaleki, Arunkumar Byravan and everyone else on the Controls team for their support.

0

Mohak Bhardwaj

@mostlymohak

3 months

@rwik_rana @BostonDynamics Thanks Rwik!

0

1