Manish Prajapat
@Manish8Prajapat
Followers
309
Following
394
Media
5
Statuses
28
Doctoral Fellow at ETH AI Center, MS in Robotics ETH Zurich (Thesis at CMS, Caltech), B Tech, Mech Eng IIT Madras, #Robotics #RL #multi_agent.
Zurich, Switzerland
Joined November 2015
Happy to share that I will present two of my recent works @ #NeurIPS2025. In this line of work we studied how to build RL agents that learn safely online (aka safe exploration).
1
1
9
Join us for the Robotics, Vision, and Controls Talks from this week! We curated a list of exceptional speakers for a series of talks focusing on robotics, computer vision, controls, and learning. Everyone is welcomed! Web: https://t.co/hxeadcCpsP Zoom: https://t.co/MGc4XLmUv1
2
16
88
With more than 8,500 satellites in orbit, Starlink provides connectivity through harsh weather conditions, network disruptions, and natural disasters. Order online in under 2 minutes.
105
323
2K
How to tackle learning under non-Markovian feedback? Check out our #ICML2024 paper, tomorrow at 1:30 PM.
How can we efficiently (approximately) solve an RL problem with non-additive trajectory rewards? In our #ICML2024 paper (session: Tue 23rd, 1.30pm), we propose a meta-algorithm that solves this problem by reducing it to a specific sequence of standard MDPs.
0
0
3
Thrilled to share our 8 conference paper contributions to @icmlconf 2024 next week. Congrats to our doctoral fellows, postdoctoral fellows, and staff members involved: @afra_amini, @Manish8Prajapat, @JavierAbadM, @DonhauserKonst, @desariky, @ImanolSchlag, D. Dmitriev, E. Bamas
2
7
21
Definitely an amazing game! Even while being on a train in Switzerland, could barely watch the scenic views 😂
what a game, could barely breathe, everything that makes sports incredible. Congrats India, so well deserved! SA was incredible. Amazing #WorldT20
0
0
1
🌟#ICLR2024 Spotlight🌟 How to learn a policy in an MDP with non-additive rewards, e.g., experiment design, exploration, etc?🤔 Excited to share our paper: Submodular RL for such challenging tasks; where standard RL fails P: https://t.co/16HH0c1pxJ W: @mutny_ml, MZ, @arkrause
0
4
19
Unfortunately, as we show, the problem is difficult to approximate in general. Nevertheless, a natural strategy of being greedy for rewards works amazingly well in many tasks. In addition, it performs provably well under some assumptions.
0
0
1
🌟#ICLR2024 Spotlight🌟 How to learn a policy in an MDP with non-additive rewards, e.g., experiment design, exploration, etc?🤔 Excited to share our paper: Submodular RL for such challenging tasks; where standard RL fails P: https://t.co/16HH0c1pxJ W: @mutny_ml, MZ, @arkrause
1
4
18
⏰ Deadline Approaching! 🚀Apply by Nov 22 to become an ETH AI Center #PhD or #Postdoc! We're hosting an EXTRA Online Q&A Session 📅Monday, Nov 20, 16:15 - 17:00 CET. Zoom link on our website 🔗 https://t.co/bBmybtshzQ Don't miss this chance to get the info you need!
0
19
39
Interested in learning how Reinforcement Learning can be applied in the real world? Come and join us at the #LaunchAIXSummit2023 tomorrow (14:30)! At our panel, we will explore the transformative impact of RL on real-world problems.@ETH_AI_Center
https://t.co/LKDK91V5tP
#RL #AI
1
10
60
.@Manish8Prajapat presented work on multi-agent learning for near-optimal coverage control, which has applications in biodiversity monitoring. SafeMaC is highly efficient & outperforms competing methods: https://t.co/PFKdjFuHC5 w/ @MatteoTurchetta Melanie Zeilinger @arkrause
2
2
5
If you are interested in Bayesian Optimization, Safety, Multi-Agent learning or Submodularity, Drop by for a chat at our poster #325 at 4 PM, #NeurIPS22.
Excited to present our work titled “Near-Optimal Multi-Agent learning for Safe Coverage Control” at NeurIPS next week. Paper: https://t.co/kyqVC9QA3h Code: https://t.co/h92BWxrnfu Work with: @MatteoTurchetta, Melanie Zeilinger, @arkrause. Thanks to @ETH_AI_Center. (1/3)
0
1
15
We propose SafeMaC that tackles this problem of a-priori unknown objective & constraints. SafeMaC achieves near-optimal coverage in finite time & guarantees safety w.h.p. We demonstrate it on a Gorilla monitoring task. It is highly sample-efficient & outperforms competing methods
0
0
2
In coverage control agents maximize coverage of some spatially distributed events. Even with known density of events, this is NP-Hard. In real-world tasks, eg bio-diversity monitoring, often density is a-priori unknown and agents face safety constraints, a-priori unknown as well.
0
0
2
Excited to present our work titled “Near-Optimal Multi-Agent learning for Safe Coverage Control” at NeurIPS next week. Paper: https://t.co/kyqVC9QA3h Code: https://t.co/h92BWxrnfu Work with: @MatteoTurchetta, Melanie Zeilinger, @arkrause. Thanks to @ETH_AI_Center. (1/3)
3
4
35
Apply now and start your PhD or Post-Doc at the ETH AI Center to shape the future of #AI and #ML with interdisciplinary AI research and open your career path to academia, industry and start-ups! Apply before Nov 30: https://t.co/bBmybtsPpo
@CSatETH @ETH
2
41
62
JOB OPENING! Do you want to use your data science and software engineering skills for a good cause? Check out our opening for a research position at the intersection of sustainable agriculture and machine learning! https://t.co/9Z3mddm9Kj
0
9
12
WE'RE HIRING! If curating and organising #inspiring events at the interfaces between #industry, #academia and #society is your passion, we're looking for YOU: https://t.co/UYzoNi0jyV
0
4
5
Only 2 weeks left to apply for the ETH AI Center Doctoral Fellowships 2022! Ready to shape the future of #AI and #MachineLearning? Apply now to the ETH AI Center Doctoral or Postdoctoral Fellowship 2022! More information on: https://t.co/2GXe56D6Bg
#phd #postdoc #education #ML
1
14
27
Looking for an opportunity to shape the future of AI and machine learning? Apply now to the ETH AI Center Doctoral or Postdoctoral Fellowship 2022! More information on: https://t.co/2GXe56D6Bg
#ethaicenter #ETHZ #AI #Machinelearning #phd #postdoc #fellowship #education
0
72
129