Saeed Rahmani

5 posts

Saeed Rahmani

Saeed Rahmani

@saeedrmd

PhD Candidate | AI and Autonomous Driving

Delft, the Netherlands Katılım Mayıs 2011
22 Takip Edilen8 Takipçiler
Saeed Rahmani retweetledi
Alex Goldie
Alex Goldie@AlexDGoldie·
1/ 🪩 Automating the discovery of new algorithms could unlock significant breakthroughs in ML research. But optimising agents for this research has been limited by too few tasks to learn from! Introducing DiscoGen, a procedural generator of algorithm discovery tasks 🧵
Alex Goldie tweet media
English
3
41
144
35K
Saeed Rahmani retweetledi
Shimon Whiteson
Shimon Whiteson@shimon8282·
Check out our new work on learning to drive in new cities without collecting any new demonstrations in that city. All we need is a simple reward function and readily available map and meta-information about the city. Self-play reinforcement learning does the rest!
Zilin Wang@zilinwang4ai

1/ 🚗 🌏 What if an autonomous vehicle could move to a new city without collecting a single human demonstration in that city? I am so excited to introduce our new work: Learning to Drive in New Cities Without Human Demonstrations.

English
0
3
23
3.6K
Saeed Rahmani retweetledi
Jakob Foerster
Jakob Foerster@j_foerst·
Using MARL to improve self driving has been a motivational example in my presentations and papers for over a decade. Today we are taking another large step in this direction and show that Multi-Agent learning can improve both realism and performance of driving policies, using minimal information from the target city (such as road layouts).
Zilin Wang@zilinwang4ai

1/ 🚗 🌏 What if an autonomous vehicle could move to a new city without collecting a single human demonstration in that city? I am so excited to introduce our new work: Learning to Drive in New Cities Without Human Demonstrations.

English
3
4
39
5.2K
Saeed Rahmani
Saeed Rahmani@saeedrmd·
Deploying an #AutonomousVehicle in a new city often requires costly data-collection. In our recent work, we address this issue by adapting a driving policy to new cities without collecting human demonstrations via Regularized self-play RL: arxiv.org/abs/2602.15891
Zilin Wang@zilinwang4ai

1/ 🚗 🌏 What if an autonomous vehicle could move to a new city without collecting a single human demonstration in that city? I am so excited to introduce our new work: Learning to Drive in New Cities Without Human Demonstrations.

English
0
0
0
18