https://openreview.net/forum?id=rXFzVRZsbt&referrer=%5Bthe%20profile%20of%20Nicolas%20Boull%C3%A9%5D(%2Fprofile%3Fid%3D~Nicolas_Boull%C3%A91)
Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling....
fine tuningdiffusion modelspolicy gradientdiscretemethods
https://deepai.org/publication/on-the-global-convergence-of-risk-averse-policy-gradient-methods-with-dynamic-time-consistent-risk-measures
01/26/23 - Risk-sensitive reinforcement learning (RL) has become a popular tool to control the risk of uncertain outcomes and ensure reliable...
on theglobal convergencerisk aversepolicy gradientmethods