Pinned Repositories
acb
A PyTorch implementation of the Anti-concentrated Confidence Bonus (ACB) for promoting exploration in deep reinforcement learning.
badge
An implementation of the BADGE batch active learning algorithm.
boostresnet
A PyTorch implementation of BoostResNet
jordanash.github.io
sharpening
warm_start
Code corresponding to 'On Warm-Starting Neural Network Training'
memoryrl
combining memory and rl
laser
The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
JordanAsh's Repositories
JordanAsh/badge
An implementation of the BADGE batch active learning algorithm.
JordanAsh/warm_start
Code corresponding to 'On Warm-Starting Neural Network Training'
JordanAsh/boostresnet
A PyTorch implementation of BoostResNet
JordanAsh/acb
A PyTorch implementation of the Anti-concentrated Confidence Bonus (ACB) for promoting exploration in deep reinforcement learning.
JordanAsh/jordanash.github.io
JordanAsh/sharpening