Understanding the compute efficiency of value functions in RL
Harry Partridge, Aly Shariff, Max Kirkby, Michael Psenka
Please rotate your device
To continue exploring this website, please rotate your device to a vertical orientation
- Harry Partridge, Aly Shariff, Max Kirkby, Michael Psenka
- AI models
The top ranked decision models in the world: mammoth-1 and elephant-1
Max Kirkby, Michael Psenka, Thomas Villeneuve, Aaryam Sharma, Charles O'Neill, Chloe Florit, Ardin Lo - Research
Mammoth-1 and Elephant-1: frontier decision models
Max Kirkby, Michael Psenka, Thomas Villeneuve, Aaryam Sharma, Charles O'Neill Why do models forget facts that they iteratively learn?
Max Kirkby, Jonathon Liu, Michael Psenka- Research
The Unreasonable Efficiency of a Single Gradient Step
Michael Psenka, Aly Shariff, Max Kirkby - Research
When does distillation help reinforcement learning?
Charles O'Neill, Michael Psenka, Max Kirkby Safety Infrastructure for Open Models
Charles O'Neill, Max Kirkby, Michael Psenka, Mudith Jayasekara