Kvfrans
kvfrans.com
As featured in
Follow
Overview
News
Technologies
Salaries
Products
People
Growth
Offices
Financials
Overview
Hi, I'm Kevin! Welcome to my webpage. I am a PhD student at Berkeley AI Research under Pieter Abbeel and Sergey Levine. Before that I did my undergrad + master's at MIT CSAIL, under Phillip Isola. My interests are in understanding deep learning and scalable self-improving systems.
News
Alchemist's Notes on Deep Learning
I recently compiled a more cleaned-up set of explanations and implementations on topics relating to deep learning and generative modelling. Check them out at https://notes.kvfrans.com/
Read more
Report
Small-Research: Tanh Activations with DDPG
When implementing DDPG-style policy extraction, we often use a tanh normalizer to bound the action space. That way the policy does not attempt to output something OOD when the Q-function is only trained on actions in -1, 1.dist = agent.actor(batch'observa
Read more
Report
Small-Research: Policy Extraction in IQL
Insight: IQL-AWR agents on 'maze2d' converge to a standard deviation of 0.4, which is much higher than expected.Hypothesis: The KL constraint of AWR prevents it from learning Gaussian policies that are centered around the optimal action.Conclusion: In dat
Read more
Report
Pro access
Upgrade to see all 21 mentions
Upgrade to a paid plan to read every media mention of this company - funding news, awards, product launches and press releases from all the outlets writing about it.
Every media mention and press release
Funding news, awards and product launches
Fresh coverage from every outlet writing about the company
Upgrade now
Cancel anytime. Secure checkout. Instant activation.