@NGavenski

PhD Student @safe_trusted_ai | Interested in #imitation_learning and #agents | Automating my way to more free time, one time-consuming project at a time.

 London
nathangavenski.github.io
Joined May 2014
  • Tweets383
  • Following147
  • Followers54
O mundo não dá voltas, ele capota!😂 reporterbrasil.org.br/2025/0…

Venda de artigos acadêmicos na internet abre brecha para crimes

Classificados, como OLX, e plataformas especializadas, como StudyBay, oferecem produção de conteúdos acadêmicos e abrem brechas para crimes

reporterbrasil.org.br
1
34
I don't know why, but having a masterclass from @JamieBGall on the beach in Brazil feels better than in London 😂😂😂
5
137
Made a watcher so I don't have to run my script manually when coding github.com/NathanGavenski/py… Discussions: discu.eu/q/https://github.co… #programming #python by @NGavenski

GitHub - NathanGavenski/python-watcher: This is a watcher to rerun scripts, execute tests and run...

This is a watcher to rerun scripts, execute tests and run lint after you change a directory or a file. - NathanGavenski/python-watcher

github.com
1
1
43
Set your reminders for the 2024 #XmasLectures, supported by @CGI_global! 🗓️ 29, 30 and 31 December 📺 BBC Four and iPlayer ⏰ 9pm In the series, @DoctorChrisVT will explore the surprising science of food – from production to digestion. Find out more: rigb.org/christmas-lectures/…
13
104
19
239
54,716
I'm always curious about what data goes into @GitHubCopilot. Today, when writing LaTeX locally, I decided to try it. My paper has nothing to do with it, so I guess papers also go into it. Nice try Copilot, nice try.
1
29
It got better
1
13
Couldn't find the original paper from this, well... back to writing.
11
If you are interested in something that allows you to run scripts automagically after modifying files, here is a package you might enjoy! New release: github.com/NathanGavenski/py…

Release 0.1.0 · NathanGavenski/python-watcher

New release 🏁 Previously, watcher-cli would not kill the running process even when stuck. Now, any events that trigger watcher-cli will kill the running process and rerun the process (no more...

github.com
1
17
Having to work extra hard to surpass your own method should not be part of writing a new paper 😅
19
Me: I can finally submit my literature review to a journal. Journal: ... Me:
31
I couldn't agree more. A supportive supervisor has greatly elevated my work and myself as a researcher in the past few years. It is night and day!
The PhD Place
@ThePhDPlace21 Dec 2024
Having a supportive supervisor makes SO MUCH difference
73
Had an amazing time at PhD Connect 2024 in Leeds, and many thanks to @turinginst for organising the event. It is always an excellent opportunity to get to know many other PhD Students and discuss different research topics!
4
117
Yesterday I had the pleasure to present my work at @ecai2024. Thanks to all the authors for the great work, @safe_trusted_ai for supporting me and allowing me to pursue my research and @KingsNMES for the resources and space that makes this work possible.
3
1
11
575
1/2 If you are interested in imitation learning and you are @ecai2024, come join me in my talk about our work "Explorative Imitation Learning: A Path Signature Approach for Continuous Environments" I will talk as part of the machine learning 2 session tomorrow (21/10)
1
1
3
418
1/2 We use exploration and path signatures to create expert-like agents few expert samples and no prior knowledge/human intervention. You can read more about it in: ebooks.iospress.nl/doi/10.32… And check our public code in: github.com/NathanGavenski/CI…

GitHub - NathanGavenski/CILO: Pytorch official implementation for Continuous Imitation Learning...

Pytorch official implementation for Continuous Imitation Learning from Observation - NathanGavenski/CILO

github.com
1
1
59
Thanks to all the authors that made this work possible @odinaldo @drmeneguzzi @michaelluck and Juarez Monteiro
1
2
38
Nathan Gavenski retweeted
Nandi@NandiSchoots20 Oct 2024
1/5 Suppose you need 40% of a model's trained parameters to keep 95% of the model’s accuracy What proportion of parameters do you need if you make the model 5x wider? 🤔 Come to tomorrow’s @ecai2024 presentations to find out!
1
6
9
1,457
Here is something I didn't know I needed 😂 next paper for sure will have loss rider graphs
Josef Dean@JosefNDean20 Aug 2024
Sure matplotlib is cool, but what if I want to load my loss curves into the 2006 hit Flash game LineRider?
1
6
406
It was a great experience to go to AAMAS and get to know so many researchers and such a beautiful place! High expectations for @ecai2024, and thrilled to present our current work there.
UKRI CDT in Safe & Trusted AI @ King's & Imperial@safe_trusted_ai15 Aug 2024
STAI CDT Student @NGavenski presented the demonstration track paper, ‘Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking’ at @AAMASconf Read about the toolkit and Nathan's conference experience 🔗#AAMAS2024 bit.ly/4fO6j4I

Nathan Gavenski presents demonstration track paper at AAMAS 2024 - Safe & Trusted AI

STAI CDT Student, Nathan Gavenski, presented the demonstration track paper, ‘Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking’, at the 23rd International...

safeandtrustedai.org
1
5
224
😂
Wolfgang Viechtbauer@wviechtb15 Sep 2022
What if all those PhDs stop just defending and actually start attacking?!?
2
62
Load more