Anthony GX-Chen
@AntChen_
PhD student at @CILVRatNYU. Prev: Master’s @mcgillu & @Mila_Quebec || RL, ML. Always neuroscience-inspired.
Can neuro-inspired ANN architectures be useful for motor control in quadruped robots? We translate neural circuits in the limbs and spinal cord of mammals into an ANN architecture controlling quadruped locomotion. w/ @venkyp2000, @LerrelPinto, @neurograce
Fascinating preprint with our "blicket detector" paradigm from Chen et al at NYU&Mila. LLM's make the same causal inference mistakes that adults make but 4 year olds don't! Models are trained on adult data, kids figure it out for themselves. im-ant.github.io/publications/g…
The original RL algorithms, inspired by natural learning, were online and incremental—they were streaming in the sense that they learned from each increment of experience as it happened, then discarded it, never to be processed again. The streaming algorithms were simple and…
Would you believe that deep RL can work without replay buffers, target networks, or batch updates? Our recent work gets deep RL agents to learn from a continuous stream of data one sample at a time without storing any sample. Joint work with @Gautham529 and @rupammahmood.