Nathan Lichtlé @nathanlichtle

PhD @UCBerkeley (@berkeley_ai) nathanlichtle.com Paris Joined May 2019

Tweets

29
Followers

124
Following

125
Likes

53

Berkeley AI Research @berkeley_ai

5 months ago

New Blog Post: Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment bair.berkeley.edu/blog/2025/03/2…

3 12 52 19K 30

Eugene Vinitsky (@RLC) 🍒🦋 @EugeneVinitsky

7 months ago

This paper has everything: large-scale empirical testing, new benchmarks, and subsequent empirical recommendations that we think might make solving imperfect information games a little easier

Nathan Lichtlé @nathanlichtle

7 months ago

This paper has everything: large-scale empirical testing, new benchmarks, and subsequent empirical recommendations that we think might make solving imperfect information games a little easier

4 9 59 13K 32

1 2 44 4K 14

Nathan Lichtlé @nathanlichtle

7 months ago

Tic-Tac-Toe... but the opponent's moves are hidden. Can you outsmart our top RL agents? Play here: nathanlichtle.com/research/2p0s

Nathan Lichtlé @nathanlichtle

7 months ago

Tic-Tac-Toe... but the opponent's moves are hidden. Can you outsmart our top RL agents? Play here: nathanlichtle.com/research/2p0s https://t.co/5KED6nCoD6

4 9 59 13K 32

1 2 11 5K 4

Download Image

Joseph Suarez 🐡 @jsuarez5341

9 months ago

x.com/i/article/1853…

8 33 362 29K 286

Amaury Hayat @Amaury_Hayat

11 months ago

Can language models be trained to find solutions to as yet unsolved mathematical problems? The answer is yes! Check our new article 🙂 1/n

François Charton @f_charton

11 months ago

Can language models be trained to find solutions to as yet unsolved mathematical problems? The answer is yes! Check our new article 🙂 1/n

15 135 683 73K 364

Download Image

1 1 11 683 3

Nathan Lichtlé @nathanlichtle

12 months ago

Another driving sim??

1 0 2 194 0

Download Video

Eugene Vinitsky (@RLC) 🍒🦋 @EugeneVinitsky

a year ago

We’re open-sourcing and arxiving GPUDrive, a GPU-accelerated 2.5D multi-agent driving simulator that runs at over a million FPS. Hundreds of scenes on one GPU means scalable multi-agent planning

19 144 928 71K 411

Download Gif

Excited to share our work about the MVT, a large-scale highway field test for which we trained autonomous vehicles to smooth out traffic flow using deep reinforcement learning, then deployed our AI controllers onto 100 vehicles in busy morning traffic. Read more below! (1/n)