Stefano Albrecht
@s_albrecht
Followers
2K
Following
194
Media
44
Statuses
225
Research in AI and machine learning for autonomous systems. MIT Press textbook: https://t.co/6j2qF00zsU Views are my own.
Joined December 2020
Internship opportunity!.Work with the ML team at @DeepFlowAI London to build LLM agentic systems for multi-agent collaboration with human and AI workers.
🚨Internship🚨: ML Engineer & Research. @DeepFlowAI London (LLMs, Agentic Systems, Multi-Agent Collaboration) — We are looking for a highly motivated intern to join our ML team led by Dr. Stefano Albrecht (Director of AI at DeepFlow). Apply here:
1
4
23
The Multi-Agent RL book has completely sold out! 😀 Reprints are now in production by @mitpress. We have updated the book with some corrections. The book PDF + errata, slides, code and exercises are available at
1
48
319
It is finally here - #RLDM2025 will happen this week in Dublin! Exciting program with talks, tutorials, workshops, posters and socials. Venue completely sold out!. The team will post daily updates on Blusky at @rldmdublin2025.bsky.social. All info at
0
0
17
Submission deadline for @RLDMDublin2025 is coming! 15 January 2025.RLDM is an interdisciplinary conference about reinforcement learning in humans, animals, and algorithms. Exciting line-up of speakers, tutorials, workshops, and socials! ➡️ @RL_Conference
0
11
33
Out NOW - Our Multi-Agent RL textbook has finally arrived in stores today!. Order from @mitpress or other book stores. Just in time for Christmas! 🙂. Lecture slides (with Tex files) and algorithm code are available from the book homepage. See Lukas' post ⬇️ for more details.
📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress!. What you get, why you should be interested and more, all below in a short 🧵👇
2
17
117
I’m pleased to announce that I have been invited to speak at a @NATO event about multi-agent systems technologies at their HQ in Brussels on the 23rd of September. I will be giving a presentation about our research in multi-agent systems and MARL, and the potential impact of.
3
2
33
Looking forward to attending the European Graduate Network Symposium 2024 at the Honda Research Institute in Germany next week!. Honda is an important partner for our research group and we're working together on exciting new projects. One of these is a new JAX-accelerated
1
1
36
RT @IIIACSIC: 🔵Join our Multi-Agent Reinforcement Learning Course running from Sept 16-19, 2024. Dive into one of the most dynamic areas o….
0
6
0
Looking forward to teaching at the Multi-Agent Reinforcement Learning (MARL) summer school hosted by @IIIACSIC in Barcelona from 16-19th September. Registration opens tomorrow and in-person spots are limited!. Why should you join? . MARL is at the cutting edge of machine.
2
11
34
Looking forward to giving a lecture about RL and Multi-agent RL this week (Wednesday!) at the 24th European Agent Systems Summer School in Dublin. Very interesting collection of topics and hackathon! 👍.#euramas #reinforcementlearning.
2
3
28
The first RLC in Amherst was such a great experience! Lots of old and new friends here. Thanks to the organisers for putting this great event together. @RL_Conference. Stay tuned for the next RLDM conference in June 2025 in Dublin, Ireland (!
0
4
38
🎉 2x RLC papers and 1x RLC workshop paper!. Delighted to share that we have had 3 papers accepted to the first Reinforcement Learning Conference @RL_Conference. 1. Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras.We propose a self-supervised auxiliary
1
15
61
🎉 We have an exciting update to our open-source MARL libraries for you!. Our popular EPyMARL library (439⭐) with highly customisable implementations for many MARL algorithms has now become even better - welcome to EPyMARL v2.0! See our new blog post for.
2
10
60
Postdoc application closing soon!.
Postdoc position in multi-modal RL and LLMs at School of Informatics, University of Edinburgh. International applicants are welcome. Deadline 23 July 2024. Details here: @InfAtEd @EDINrobotics.
0
3
15
🎉 Exciting work from our lab on improving RL generalisation!. DRED is a novel framework that enhances zero-shot transfer in RL when the number of environment instances available during training is limited. Check it out at #ICML2024!.
🤔 Can RL agents generalise effectively with fewer training levels? Our #ICML2024 paper demonstrates how to substantially enhance the transfer capabilities of RL agents by acting on the sampling and generation of individual environment instances (or "levels"). We introduce
0
2
43
New PhD position in Multi-agent RL funded by @Leonardo_live. Start between Sep'24 to Jan'25, funded for 3.5 years, working with our group and Leonardo. Candidate must *not require ATAS To apply/questions: email CV, transcripts, and research ideas to me.
0
8
40
(2/2) You can check out a selection of past talks from @jl_marino @dabelcs @pcastr @geraudnt and @MGerstgrasser and many others! 🤖.
0
0
12
(1/2) Exciting news - our RL Reading Group meetings will now be on YouTube 🎉 Subscribe to stay up-to-date with SOTA RL research: Our (virtual) meetings are open to all, sign up here!
1
12
74