robin ranjit singh chauhanTwitter Spaces that Do Not SuckAs we learned back when Clubhouse launched, audio-only rooms can be a fun and informative medium.Dec 31, 2022Dec 31, 2022
robin ranjit singh chauhanGoal Misgeneralization, Pied Pipers, and Causal ModelsDeepMind AGI safety researcher Rohin Shah recently published an interesting paper on how agents can learn the wrong goal, described in this…Dec 22, 2022Dec 22, 2022
robin ranjit singh chauhanWhat sucked about the Deep RL Poster Sessions at NeurIPS 2018NeurIPS 2018 in Montreal was my first experience with the NeurIPS series of conferences. I was there primarily for Deep RL workshop and as…Apr 23, 2019Apr 23, 2019
robin ranjit singh chauhanCuriosity, Reward Sign Bias, and Political Orientation in Reinforcement LearningA common metaphor to explain exploit/explore tradeoff in bandit problems is that you are in a new town (say Montreal), and have tried 2 of…Jan 12, 2019Jan 12, 2019
robin ranjit singh chauhan“Robustify” RL: Uber, Go-Explore, and Research as RL with SOTA rewardsRecently at NeurIPS 2018 in Montreal, I witnessed Uber’s Jeff Clune present Go-Explore, their solution to Montezuma’s Revenge, the Atari…Dec 30, 2018Dec 30, 2018
robin ranjit singh chauhanBefore you ask for help with your data science codeBefore posting your question, first try getting to YES to all these questions:Mar 22, 2018Mar 22, 2018
robin ranjit singh chauhanA Tale of Two Models: “Traditional” Machine Learning vs Deep LearningI originally shared this presentation with Vancouver’s Learn Data Science group on Nov 3 2017, which meets at the VentureLabs space in…Nov 20, 2017Nov 20, 2017
robin ranjit singh chauhaninHackerNoon.comHandy R Markdown Hacks for emailI love R and R markdown. But when I went to produce HTML email reports using Rmd using something simple like this:Sep 12, 20161Sep 12, 20161
robin ranjit singh chauhanadvice to people starting a career in softwareUrmila Nadkarni, a friend and software engineer I used to work with at Microsoft, recently asked her network what career advice we wish we…Dec 13, 2015Dec 13, 2015
robin ranjit singh chauhanHolacracy CrashcourseTension-driven. Distributed authority. Nested circles vs stacked pyramids.Oct 13, 2015Oct 13, 2015