
Rupam Mahmood
@rupammahmood
Assistant Professor @ualberta, PI @rlai_lab, Canada CIFAR AI Chair @CIFAR_News, Fellow @amiithinks, working on continual learning, RL, & robot learning
ID: 2271048799
https://armahmood.github.io/ 01-01-2014 02:03:53
321 Tweet
739 Followers
240 Following






I wrote a blog post on how we can see policy gradient methods from an operators perspective, and how this provides us with an interpolation between REINFORCE and value-based methods. Blog post: mcmachado.info/?p=248 Paper: arxiv.org/abs/2006.11266 @le_roux_nicolas Dibya Ghosh







.Tony Zador since your post is making a resurgence... a video of an animal overcoming its innate drive to wash its food first... I’d call that an adaptive intelligent system :) youtube.com/watch?v=rfbb4y…


Just discovered: the lost thesis of Dennis Ritchie, creator of the C programming language & co-creator of Unix. Read it here: bit.ly/RitchiePhD Ritchie never got his PhD b/c he didn't want to pay Harvard the thesis binding fee. bit.ly/2GBr1Jm (v/IEEE Spectrum)




