Daphne Cornelisse
@daphne-cornelisse.bsky.social
๐ค 289
๐ฅ 52
๐ 16
PhD student at NYU | Building human-like agents |
https://www.daphne-cornelisse.com/
What if you could train agents on a ๐ฑ๐ฒ๐ฐ๐ฎ๐ฑ๐ฒ of driving experience in ๐๐ป๐ฑ๐ฒ๐ฟ ๐ฎ๐ป ๐ต๐ผ๐๐ฟ, on a single GPU? Excited to share ๐๐ช๐๐๐๐ง๐ฟ๐ง๐๐ซ๐ 2.0: A fast, friendly driving simulator with RL training via PufferLib at ๐ฏ๐ฌ๐ฌ๐ ๐๐๐ฒ๐ฝ๐/๐๐ฒ๐ฐ ๐ก + ๐
youtu.be/LfQ324R-cbE?...
loading . . .
PufferDrive 2.0 release
YouTube video by Daphne Cornelisse
https://youtu.be/LfQ324R-cbE?si=hn_A1w67zEOHv3g_
9 days ago
2
50
11
reposted by
Daphne Cornelisse
Mark Ho | Hiring postdocs + PhD students
about 2 months ago
Excited to share a new preprint, accepted as a spotlight at
#NeurIPS2025
! Humans are imperfect decision-makers, and autonomous systems should understand how we deviate from idealized rationality Our paper aims to address this! ๐๐ง โจ
arxiv.org/abs/2510.25951
a ๐งตโคต๏ธ
loading . . .
Estimating cognitive biases with attention-aware inverse planning
People's goal-directed behaviors are influenced by their cognitive biases, and autonomous systems that interact with people should be aware of this. For example, people's attention to objects in their...
https://arxiv.org/abs/2510.25951
1
62
16
Rapid RL experimentation is great. But how do you catch silent errors before they slip by? In this post, I share tools and habits that help me move quickly from idea to result without sacrificing reliability.
loading . . .
How to catch subtle RL bugs before they catch you
Tools and habits for reliable, fast RL experimentation and development
https://open.substack.com/pub/daphnecornelisse/p/how-to-catch-subtle-rl-bugs-before?r=2n3hgw&utm_campaign=post&utm_medium=web&showWelcomeOnShare=false
3 months ago
0
41
6
reposted by
Daphne Cornelisse
Eugene Vinitsky ๐
4 months ago
The single biggest epistemic challenge in the internet era is remaining calibrated about what "normal" people think while the internet throws up an infinite wall of crazy. Thousands of people sharing an absurd opinion on the internet tells you very little!
8
128
18
Overnight runs are the overnight oats of research โ prep, forget, and rewarding by morning
9 months ago
0
13
4
reposted by
Daphne Cornelisse
Eugene Vinitsky ๐
10 months ago
Building a "human-level" simulated driver that zero-shot generalizes to many benchmarks: a fun interview with
@natolambert.bsky.social
www.youtube.com/watch?v=2Q66...
loading . . .
Self-play for Self-driving and where Scaling Reinforcement Learning is Heading with Eugene Vinitsky
YouTube video by Interconnects AI
https://www.youtube.com/watch?v=2Q66uIRMEnc&ab_channel=InterconnectsAI
0
18
4
Sim agents are key for developing autonomous systems for safety-critical systems, like self-driving cars. We're open-sourcing sim agents that achieve a 99.8% success rate with < 0.8% failures on the Waymo Dataset. These agents are built through scaling self-play.
loading . . .
10 months ago
3
34
6
GPUDrive got accepted to ICLR 2025! With that, we release GPUDrive v0.4.0! ๐จ You can now install the repo and run your first fast PPO experiment in under 10 minutes. Iโm honestly so excited about the new opportunities and research the sim makes possible. ๐ 1/2
loading . . .
11 months ago
2
45
5
reposted by
Daphne Cornelisse
Eugene Vinitsky ๐
11 months ago
A large group of us (spearheaded by Denizalp Goktas) have put out a position paper on paths towards foundation models for strategic decision-making. Language models still lack these capabilities so we'll need to build them:
hal.science/hal-04925309...
2
33
7
you reached the end!!
feeds!
log in