Taylor W. Killian
@twkillian.bsky.social
Senior Research Scientist @MBZUAI. Focused on decision making under uncertainty, guided by practical problems in healthcare, reasoning, and biology.
Reposted by Taylor W. Killian
The workshops are maybe the best part of RLC. Bring us your workshops that could never happen anywhere else!
We're thrilled to share that the Call for Workshops for this year's @rl-conference.bsky.social is now live!
As Workshop co-chair (alongside the wonderful Raksha Kumaraswamy and @claireve.bsky.social) we are looking forward to seeing the proposals for workshops that we receive.
LINK IN NEXT POST
As Workshop co-chair (alongside the wonderful Raksha Kumaraswamy and @claireve.bsky.social) we are looking forward to seeing the proposals for workshops that we receive.
LINK IN NEXT POST
February 13, 2026 at 10:07 PM
The workshops are maybe the best part of RLC. Bring us your workshops that could never happen anywhere else!
Reposted by Taylor W. Killian
3 weeks to get your RLC papers in shape! And to get the word out to those who have yet to experience an RLC review process.
Quick reminder for everyone grinding on their RLC 2026 papers, only ~3 weeks to go!
The submission site opens in just a few days (Feb 17).
Deadlines:
⏳ March 1 (AoE): Abstract Submission
⏳ March 5 (AoE): Full Paper Submission
Good luck with the final changes!
The submission site opens in just a few days (Feb 17).
Deadlines:
⏳ March 1 (AoE): Abstract Submission
⏳ March 5 (AoE): Full Paper Submission
Good luck with the final changes!
Hi RL Enthusiasts!
RLC is coming to Montreal, Quebec, in the summer: Aug 16–19, 2026!
Call for Papers is up now:
Abstract: Mar 1 (AOE)
Submission: Mar 5 (AOE)
Excited to see what you’ve been up to - Submit your best work!
rl-conference.cc/callforpaper...
Please share widely!
RLC is coming to Montreal, Quebec, in the summer: Aug 16–19, 2026!
Call for Papers is up now:
Abstract: Mar 1 (AOE)
Submission: Mar 5 (AOE)
Excited to see what you’ve been up to - Submit your best work!
rl-conference.cc/callforpaper...
Please share widely!
February 13, 2026 at 4:14 AM
3 weeks to get your RLC papers in shape! And to get the word out to those who have yet to experience an RLC review process.
Reposted by Taylor W. Killian
🚀 Excited to share REPPO, a new on-policy RL agent!
TL;DR: Replace PPO with REPPO for fewer hyperparameter headaches and more robust training.
REPPO, led by @cvoelcker.bsky.social, will be presented at ICLR 2026. How does it work? 🧵👇
TL;DR: Replace PPO with REPPO for fewer hyperparameter headaches and more robust training.
REPPO, led by @cvoelcker.bsky.social, will be presented at ICLR 2026. How does it work? 🧵👇
February 13, 2026 at 7:29 PM
🚀 Excited to share REPPO, a new on-policy RL agent!
TL;DR: Replace PPO with REPPO for fewer hyperparameter headaches and more robust training.
REPPO, led by @cvoelcker.bsky.social, will be presented at ICLR 2026. How does it work? 🧵👇
TL;DR: Replace PPO with REPPO for fewer hyperparameter headaches and more robust training.
REPPO, led by @cvoelcker.bsky.social, will be presented at ICLR 2026. How does it work? 🧵👇
We're thrilled to share that the Call for Workshops for this year's @rl-conference.bsky.social is now live!
As Workshop co-chair (alongside the wonderful Raksha Kumaraswamy and @claireve.bsky.social) we are looking forward to seeing the proposals for workshops that we receive.
LINK IN NEXT POST
As Workshop co-chair (alongside the wonderful Raksha Kumaraswamy and @claireve.bsky.social) we are looking forward to seeing the proposals for workshops that we receive.
LINK IN NEXT POST
February 13, 2026 at 9:50 PM
We're thrilled to share that the Call for Workshops for this year's @rl-conference.bsky.social is now live!
As Workshop co-chair (alongside the wonderful Raksha Kumaraswamy and @claireve.bsky.social) we are looking forward to seeing the proposals for workshops that we receive.
LINK IN NEXT POST
As Workshop co-chair (alongside the wonderful Raksha Kumaraswamy and @claireve.bsky.social) we are looking forward to seeing the proposals for workshops that we receive.
LINK IN NEXT POST
Reposted by Taylor W. Killian
Shipping a copy of Kuhn's "Structure of Scientific Revolutions" to every ICML meta-reviewer
May 1, 2025 at 12:59 PM
Shipping a copy of Kuhn's "Structure of Scientific Revolutions" to every ICML meta-reviewer
We're putting in final planning and preparation steps this week to be ready for #ICLR2025. I'm excited to be attending, in part to help represent @mbzuai.bsky.social and @llm360.bsky.social as well as recruit Research Scientists and Engineers to our new lab in the Bay Area! (see next for more info)
April 16, 2025 at 5:40 PM
We're putting in final planning and preparation steps this week to be ready for #ICLR2025. I'm excited to be attending, in part to help represent @mbzuai.bsky.social and @llm360.bsky.social as well as recruit Research Scientists and Engineers to our new lab in the Bay Area! (see next for more info)
I used to dream of days like this.
Mowed the lawn, trimmed some hedges, pruned a few trees to let more sun into our yard, picked the rest of our orange tree (we yielded 658 🍊this year!) had the kids help clean up the branches, etc. #suburbandadsaturdays
Mowed the lawn, trimmed some hedges, pruned a few trees to let more sun into our yard, picked the rest of our orange tree (we yielded 658 🍊this year!) had the kids help clean up the branches, etc. #suburbandadsaturdays
March 22, 2025 at 8:33 PM
I used to dream of days like this.
Mowed the lawn, trimmed some hedges, pruned a few trees to let more sun into our yard, picked the rest of our orange tree (we yielded 658 🍊this year!) had the kids help clean up the branches, etc. #suburbandadsaturdays
Mowed the lawn, trimmed some hedges, pruned a few trees to let more sun into our yard, picked the rest of our orange tree (we yielded 658 🍊this year!) had the kids help clean up the branches, etc. #suburbandadsaturdays
Reposted by Taylor W. Killian
Real-world RL for the public good! Love to see it!
A year later of a multi-agent RL controlled variable speed limit system:
arxiv.org/abs/2503.01017
Fewer crashes, quicker responses, quicker warnings
arxiv.org/abs/2503.01017
Fewer crashes, quicker responses, quicker warnings
Real-World Deployment and Assessment of a Multi-Agent Reinforcement Learning-Based Variable Speed Limit Control System
This article presents the first field deployment of a multi-agent reinforcement learning (MARL) based variable speed limit (VSL) control system on Interstate 24 (I-24) near Nashville, Tennessee. We de...
arxiv.org
March 12, 2025 at 4:20 AM
Real-world RL for the public good! Love to see it!
Reposted by Taylor W. Killian
A year later of a multi-agent RL controlled variable speed limit system:
arxiv.org/abs/2503.01017
Fewer crashes, quicker responses, quicker warnings
arxiv.org/abs/2503.01017
Fewer crashes, quicker responses, quicker warnings
Real-World Deployment and Assessment of a Multi-Agent Reinforcement Learning-Based Variable Speed Limit Control System
This article presents the first field deployment of a multi-agent reinforcement learning (MARL) based variable speed limit (VSL) control system on Interstate 24 (I-24) near Nashville, Tennessee. We de...
arxiv.org
March 12, 2025 at 2:14 AM
A year later of a multi-agent RL controlled variable speed limit system:
arxiv.org/abs/2503.01017
Fewer crashes, quicker responses, quicker warnings
arxiv.org/abs/2503.01017
Fewer crashes, quicker responses, quicker warnings
Reviewing a paper right now and I'm having lots of "I wish that I'd written this!" feelings. Great sign for the authors tbh.
March 12, 2025 at 4:18 AM
Reviewing a paper right now and I'm having lots of "I wish that I'd written this!" feelings. Great sign for the authors tbh.
Reposted by Taylor W. Killian
Congratulations Andy and Rich! You've given RL yet another place in the history books. I can't imagine how you're feeling right now, but it must be amazing to reflect on how far the ideas have come, especially after all the care and dedication you gave them.
awards.acm.org/about/2024-t...
awards.acm.org/about/2024-t...
awards.acm.org
March 5, 2025 at 9:20 PM
Congratulations Andy and Rich! You've given RL yet another place in the history books. I can't imagine how you're feeling right now, but it must be amazing to reflect on how far the ideas have come, especially after all the care and dedication you gave them.
awards.acm.org/about/2024-t...
awards.acm.org/about/2024-t...
As I've started down the RL+LLM rabbit hole (for reals this time), this blog post by TensorZero is absolutely compelling. It's nice to see clear thinking conceptual framing that at once open the doors to new research but also leverages existing insights:
www.tensorzero.com/blog/think-o...
www.tensorzero.com/blog/think-o...
Think of LLM Applications as POMDPs — Not Agents · TensorZero
Think of LLM Applications as POMDPs — Not Agents
www.tensorzero.com
March 4, 2025 at 10:29 PM
As I've started down the RL+LLM rabbit hole (for reals this time), this blog post by TensorZero is absolutely compelling. It's nice to see clear thinking conceptual framing that at once open the doors to new research but also leverages existing insights:
www.tensorzero.com/blog/think-o...
www.tensorzero.com/blog/think-o...
Struggled to find a paper to recommend to authors that would strengthen their claims while writing a review. Used @GeminiApp and @youdotcom to no success. Reluctantly pulled up @ChatGPTapp, nailed it in the first returned result. #HesitantAboutLLMsButTryingToLearn
a man with a beard is saying he can 't keep getting away with it !
ALT: a man with a beard is saying he can 't keep getting away with it !
media.tenor.com
March 3, 2025 at 5:19 AM
Struggled to find a paper to recommend to authors that would strengthen their claims while writing a review. Used @GeminiApp and @youdotcom to no success. Reluctantly pulled up @ChatGPTapp, nailed it in the first returned result. #HesitantAboutLLMsButTryingToLearn
Reposted by Taylor W. Killian
"Scaling laws" tries to piggyback on physics where the scaling laws are resultant from statistical limits. To call them "laws" rather than "empirical scaling curves" is real iffy
February 28, 2025 at 6:41 PM
"Scaling laws" tries to piggyback on physics where the scaling laws are resultant from statistical limits. To call them "laws" rather than "empirical scaling curves" is real iffy
Day 1 with @mbzuai.bsky.social as we start building out a new non-profit, open research lab in the Bay Area. Lots to learn and my head is spinning but I’m excited to get started pushing the boundaries of what we know about reasoning and decision making under uncertainty.
February 24, 2025 at 11:22 PM
Day 1 with @mbzuai.bsky.social as we start building out a new non-profit, open research lab in the Bay Area. Lots to learn and my head is spinning but I’m excited to get started pushing the boundaries of what we know about reasoning and decision making under uncertainty.
Reposted by Taylor W. Killian
We've built a simulated driving agent that we trained on 1.6 billion km of driving with no human data.
It is SOTA on every planning benchmark we tried.
In self-play, it goes 20 years between collisions.
It is SOTA on every planning benchmark we tried.
In self-play, it goes 20 years between collisions.
February 6, 2025 at 6:34 PM
We've built a simulated driving agent that we trained on 1.6 billion km of driving with no human data.
It is SOTA on every planning benchmark we tried.
In self-play, it goes 20 years between collisions.
It is SOTA on every planning benchmark we tried.
In self-play, it goes 20 years between collisions.
Reposted by Taylor W. Killian
arxiv.org/abs/2502.03349
Awesome planning results by Vladlen Koltun's new lab (@twkillian.bsky.social, @eugenevinitsky.bsky.social @senerozan.bsky.social and others) that everyone working on driving should read.
Lots of details are in the Appendix.
Awesome planning results by Vladlen Koltun's new lab (@twkillian.bsky.social, @eugenevinitsky.bsky.social @senerozan.bsky.social and others) that everyone working on driving should read.
Lots of details are in the Appendix.
Robust Autonomy Emerges from Self-Play
Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...
arxiv.org
February 6, 2025 at 4:14 PM
arxiv.org/abs/2502.03349
Awesome planning results by Vladlen Koltun's new lab (@twkillian.bsky.social, @eugenevinitsky.bsky.social @senerozan.bsky.social and others) that everyone working on driving should read.
Lots of details are in the Appendix.
Awesome planning results by Vladlen Koltun's new lab (@twkillian.bsky.social, @eugenevinitsky.bsky.social @senerozan.bsky.social and others) that everyone working on driving should read.
Lots of details are in the Appendix.
This afternoon I've been putting finishing touches on a talk that I've been invited to give at my undergrad Alma Mater (BYU Math) next Tues.
Since graduating, I've been hoping for an opportunity to return & share how my career has grown from the solid foundation I gained there. I'm really excited!
Since graduating, I've been hoping for an opportunity to return & share how my career has grown from the solid foundation I gained there. I'm really excited!
January 30, 2025 at 10:31 PM
This afternoon I've been putting finishing touches on a talk that I've been invited to give at my undergrad Alma Mater (BYU Math) next Tues.
Since graduating, I've been hoping for an opportunity to return & share how my career has grown from the solid foundation I gained there. I'm really excited!
Since graduating, I've been hoping for an opportunity to return & share how my career has grown from the solid foundation I gained there. I'm really excited!
Reposted by Taylor W. Killian
Last year's workshops were some of the most unique, weird, exciting ones I've ever attending from "Finding the Frame" to "RL Beyond Rewards" to "Deployable RL". I'm so excited for this year's unexpected entrants.
RLC call for workshops is out rl-conference.cc/callforworks...!
Submissions open on Feb 3rd, deadline on March 7, with the workshops on Aug. 5th. Last year's workshops were inimitable and we @claireve.bsky.social and Josiah Hanna) look forward to your amazing proposals
Submissions open on Feb 3rd, deadline on March 7, with the workshops on Aug. 5th. Last year's workshops were inimitable and we @claireve.bsky.social and Josiah Hanna) look forward to your amazing proposals
RLJ | RLC Call for Workshops
rl-conference.cc
January 29, 2025 at 4:07 PM
Last year's workshops were some of the most unique, weird, exciting ones I've ever attending from "Finding the Frame" to "RL Beyond Rewards" to "Deployable RL". I'm so excited for this year's unexpected entrants.
There's not much that is as disappointing as a scam call when you're expecting to hear from someone with a number you don't know...
January 28, 2025 at 10:00 PM
There's not much that is as disappointing as a scam call when you're expecting to hear from someone with a number you don't know...
My bound and published PhD thesis arrived in the mail today. It's an amazing and overwhelming feeling to hold the product of 5 years of work in my hands.
January 24, 2025 at 11:33 PM
My bound and published PhD thesis arrived in the mail today. It's an amazing and overwhelming feeling to hold the product of 5 years of work in my hands.
It's that time of year where reviewer invitations start piling up. I'm excited to contribute to the success of our research venues and am especially looking forward to the submissions I get the chance to review, especially those coming from @rl-conference.bsky.social!
January 22, 2025 at 6:42 AM
It's that time of year where reviewer invitations start piling up. I'm excited to contribute to the success of our research venues and am especially looking forward to the submissions I get the chance to review, especially those coming from @rl-conference.bsky.social!
Reposted by Taylor W. Killian
My actual favorite niche starter pack here:
go.bsky.app/2Gibu1a
go.bsky.app/2Gibu1a
January 20, 2025 at 8:17 PM
My actual favorite niche starter pack here:
go.bsky.app/2Gibu1a
go.bsky.app/2Gibu1a