Excited to share that our paper, Zero-Shot Reinforcement Learning from Low Quality Data, was accepted at #NeurIPS2024 🔥
Looking forward to chatting about it in Vancouver! 🇨🇦
Thanks, in particular, to my co-author Tom Bewley for all his help throughout the project.
It's dedicated to the late Barry Sealey CBE and Helen Sealey whose funding of my earlier postgraduate studies opened the door to a PhD. I'm hugely indebted to them for their kindness and generosity.
Check out our new paper: Low Emission Building Control with Zero-Shot Reinforcement Learning. In it we present PEARL (Probabilistic Emission-Abating Reinforcement Learning), a new algorithm that, given access to a few sensors, can reduce emissions from buildings by up to 31%.
Introducing The Metis List: a live leaderboard of 100 top AI researchers, ranked by their peers.
We include:
- Education
- Citation count
- Current company
- # of Dwarkesh appearances
- Notable work
Check it out at MetisList dot com
By my count there are exactly zero (!) modules covering LLMs across the engineering and computer science departments at Cambridge.
There are a total of three (!) modules covering deep learning. AlexNet is now 12 years old.
The reluctance to innovate is embarrassing!
I fucking love CMU. Looking through the course catalog, there's like >25 courses that cover LLMs and topics on the frontier of AI. This is what happens when you give Machine Learning, Language Technology, Robotics, etc their own entire departments, as god intended 🫡
I’m in Whistler/Vancouver for #NeurIPS2024, and I’ll be around all week to chat RL. Swing by our poster on Friday, or hit me up on here and we can find time for a coffee!
Poster #6008
West Ballroom A-D
Friday 13th Dec 4:30-7:30pm
More details below.