Miguel Vasco
@miguelvasco.bsky.social
Postdoc at @kthuniversity.bsky.social.
Past: @gaipslab.bsky.social; Sony AI.
Interested in all things RL and Multimodal.
miguelvasco.com
Past: @gaipslab.bsky.social; Sony AI.
Interested in all things RL and Multimodal.
miguelvasco.com
Pinned
Miguel Vasco
@miguelvasco.bsky.social
· Apr 15
👾👾 We are happy to announce the first Reinforcement Learning and Video Games (RLVG) Workshop at @rl-conference.bsky.social 2025! 🎮🎮
For more information and the call for papers: sites.google.com/view/rlvg-wo...
More details coming soon!
For more information and the call for papers: sites.google.com/view/rlvg-wo...
More details coming soon!
It’s been 10 years since the Atari DQN Nature paper! What better way to celebrate this milestone than with a dedicated workshop on RL and Video Games at @rl-conference.bsky.social? 🎮🎮
Join us to discuss how video games can be used to address fundamental RL problems and how RL can be used in Games!
Join us to discuss how video games can be used to address fundamental RL problems and how RL can be used in Games!
Reposted by Miguel Vasco
Missed our workshop at @rl-conference.bsky.social?
Watch all keynote presentations and the panel discussion on YouTube:
youtube.com/playlist?lis...
Big thanks to our awesome speakers: @togelius.bsky.social, @jmac-ai.bsky.social, Roberta Raileanu, Michael Bowling and @pcastr.bsky.social!
Watch all keynote presentations and the panel discussion on YouTube:
youtube.com/playlist?lis...
Big thanks to our awesome speakers: @togelius.bsky.social, @jmac-ai.bsky.social, Roberta Raileanu, Michael Bowling and @pcastr.bsky.social!
RLVG Sessions @ RLC 2025 - YouTube
Recorded sessions of the Reinforcement Learning and Video Games (RLVG) workshop at the Reinforcement Learning Conference (RLC), 2025. Recorded on August 5, 2025
youtube.com
September 25, 2025 at 9:53 AM
Missed our workshop at @rl-conference.bsky.social?
Watch all keynote presentations and the panel discussion on YouTube:
youtube.com/playlist?lis...
Big thanks to our awesome speakers: @togelius.bsky.social, @jmac-ai.bsky.social, Roberta Raileanu, Michael Bowling and @pcastr.bsky.social!
Watch all keynote presentations and the panel discussion on YouTube:
youtube.com/playlist?lis...
Big thanks to our awesome speakers: @togelius.bsky.social, @jmac-ai.bsky.social, Roberta Raileanu, Michael Bowling and @pcastr.bsky.social!
Conference rejections: hurts a bit but it's fine.
Radiohead rejections: I'll be crying in a corner all night
Radiohead rejections: I'll be crying in a corner all night
September 10, 2025 at 7:14 PM
Conference rejections: hurts a bit but it's fine.
Radiohead rejections: I'll be crying in a corner all night
Radiohead rejections: I'll be crying in a corner all night
Reposted by Miguel Vasco
This one's been a long time coming.
In this post on Decisions & Dragons I answer "Should we abandon RL?"
The answer is obviously no, but people ask because they have a fundamental misunderstanding of what RL is.
RL is a problem, not an approach.
www.decisionsanddragons.com/posts/should...
In this post on Decisions & Dragons I answer "Should we abandon RL?"
The answer is obviously no, but people ask because they have a fundamental misunderstanding of what RL is.
RL is a problem, not an approach.
www.decisionsanddragons.com/posts/should...
August 15, 2025 at 11:30 PM
This one's been a long time coming.
In this post on Decisions & Dragons I answer "Should we abandon RL?"
The answer is obviously no, but people ask because they have a fundamental misunderstanding of what RL is.
RL is a problem, not an approach.
www.decisionsanddragons.com/posts/should...
In this post on Decisions & Dragons I answer "Should we abandon RL?"
The answer is obviously no, but people ask because they have a fundamental misunderstanding of what RL is.
RL is a problem, not an approach.
www.decisionsanddragons.com/posts/should...
The @rl-conference.bsky.social is always the best time of the year for a RL researcher!
This year I had a blast co-organizing the @rlvgworkshop.bsky.social, alongside amazing people! A huge thanks to our keynote speakers and everyone who joined the discussion.
Can’t wait for Montreal next year!
This year I had a blast co-organizing the @rlvgworkshop.bsky.social, alongside amazing people! A huge thanks to our keynote speakers and everyone who joined the discussion.
Can’t wait for Montreal next year!
August 12, 2025 at 2:06 PM
The @rl-conference.bsky.social is always the best time of the year for a RL researcher!
This year I had a blast co-organizing the @rlvgworkshop.bsky.social, alongside amazing people! A huge thanks to our keynote speakers and everyone who joined the discussion.
Can’t wait for Montreal next year!
This year I had a blast co-organizing the @rlvgworkshop.bsky.social, alongside amazing people! A huge thanks to our keynote speakers and everyone who joined the discussion.
Can’t wait for Montreal next year!
Reposted by Miguel Vasco
We’re excited to announce our final keynote speaker: @michaelhbowling.bsky.social (University of Alberta). 🎲🃏
In this talk, he will explore what drew him to explore using 40-year-old video games to test RL agents!
Join us at @rl-conference.bsky.social to find out more about the Atari Benchmark!
In this talk, he will explore what drew him to explore using 40-year-old video games to test RL agents!
Join us at @rl-conference.bsky.social to find out more about the Atari Benchmark!
July 29, 2025 at 2:45 PM
We’re excited to announce our final keynote speaker: @michaelhbowling.bsky.social (University of Alberta). 🎲🃏
In this talk, he will explore what drew him to explore using 40-year-old video games to test RL agents!
Join us at @rl-conference.bsky.social to find out more about the Atari Benchmark!
In this talk, he will explore what drew him to explore using 40-year-old video games to test RL agents!
Join us at @rl-conference.bsky.social to find out more about the Atari Benchmark!
Reposted by Miguel Vasco
We’re excited to announce our next speaker: @pcastr.bsky.social (Google DeepMind, Mila) 🎮🕹️
His research tackles core challenges in deep RL for real-world impact, like network scalability and plasticity loss!
Join us at @rl-conference.bsky.social to learn more about Pablo’s work!
His research tackles core challenges in deep RL for real-world impact, like network scalability and plasticity loss!
Join us at @rl-conference.bsky.social to learn more about Pablo’s work!
July 24, 2025 at 6:10 PM
We’re excited to announce our next speaker: @pcastr.bsky.social (Google DeepMind, Mila) 🎮🕹️
His research tackles core challenges in deep RL for real-world impact, like network scalability and plasticity loss!
Join us at @rl-conference.bsky.social to learn more about Pablo’s work!
His research tackles core challenges in deep RL for real-world impact, like network scalability and plasticity loss!
Join us at @rl-conference.bsky.social to learn more about Pablo’s work!
Reposted by Miguel Vasco
We’re excited to announce our next keynote speaker:
@neuroai.bsky.social (Microsoft Research) 🧠
Ida studies how humans and AI build world models for memory, exploration, and planning. Her talk will show how game-playing AI reveals insights into human and artificial cognition.
Join us at #RLC2025!
@neuroai.bsky.social (Microsoft Research) 🧠
Ida studies how humans and AI build world models for memory, exploration, and planning. Her talk will show how game-playing AI reveals insights into human and artificial cognition.
Join us at #RLC2025!
July 18, 2025 at 10:24 AM
We’re excited to announce our next keynote speaker:
@neuroai.bsky.social (Microsoft Research) 🧠
Ida studies how humans and AI build world models for memory, exploration, and planning. Her talk will show how game-playing AI reveals insights into human and artificial cognition.
Join us at #RLC2025!
@neuroai.bsky.social (Microsoft Research) 🧠
Ida studies how humans and AI build world models for memory, exploration, and planning. Her talk will show how game-playing AI reveals insights into human and artificial cognition.
Join us at #RLC2025!
Reposted by Miguel Vasco
We’re excited to announce our next speaker: Roberta Raileanu ( Google DeepMind)!
Roberta will discuss the history and future of NetHack, the iconic roguelike that continues to challenge RL and LLM agents alike. ⚔️
Join us to learn how we can develop agents capable of tackling open-endedness!
Roberta will discuss the history and future of NetHack, the iconic roguelike that continues to challenge RL and LLM agents alike. ⚔️
Join us to learn how we can develop agents capable of tackling open-endedness!
July 11, 2025 at 3:56 PM
We’re excited to announce our next speaker: Roberta Raileanu ( Google DeepMind)!
Roberta will discuss the history and future of NetHack, the iconic roguelike that continues to challenge RL and LLM agents alike. ⚔️
Join us to learn how we can develop agents capable of tackling open-endedness!
Roberta will discuss the history and future of NetHack, the iconic roguelike that continues to challenge RL and LLM agents alike. ⚔️
Join us to learn how we can develop agents capable of tackling open-endedness!
Reposted by Miguel Vasco
We’re excited to announce our first speaker: James MacGlashan (@jmac-ai.bsky.social), from Sony AI! 🚀
James led the development of GT Sophy, a superhuman RL racing agent in Gran Turismo!
Join his talk to learn about how GT Sophy was used as an opponent in GT7 and what’s next for RL in gaming.
James led the development of GT Sophy, a superhuman RL racing agent in Gran Turismo!
Join his talk to learn about how GT Sophy was used as an opponent in GT7 and what’s next for RL in gaming.
July 9, 2025 at 3:40 PM
We’re excited to announce our first speaker: James MacGlashan (@jmac-ai.bsky.social), from Sony AI! 🚀
James led the development of GT Sophy, a superhuman RL racing agent in Gran Turismo!
Join his talk to learn about how GT Sophy was used as an opponent in GT7 and what’s next for RL in gaming.
James led the development of GT Sophy, a superhuman RL racing agent in Gran Turismo!
Join his talk to learn about how GT Sophy was used as an opponent in GT7 and what’s next for RL in gaming.
Reposted by Miguel Vasco
Two days left to submit to our Reinforcement Learning and Video Game workshop at @rl-conference.bsky.social !
Join us in discussing the bright future of RL and Video Games!
Join us in discussing the bright future of RL and Video Games!
a video game scene with crash bandicoot and a totem pole in the background
ALT: a video game scene with crash bandicoot and a totem pole in the background
media.tenor.com
June 4, 2025 at 1:48 PM
Two days left to submit to our Reinforcement Learning and Video Game workshop at @rl-conference.bsky.social !
Join us in discussing the bright future of RL and Video Games!
Join us in discussing the bright future of RL and Video Games!
“A delayed paper is eventually good; a bad paper is forever bad”
- Shigeru Miyamoto
One more week to submit to our amazing RL and video games workshop!
- Shigeru Miyamoto
One more week to submit to our amazing RL and video games workshop!
❗️❗️submission deadline is extended!
⌛ New Submission Deadline: June 6th, AoE
Find out more here: sites.google.com/view/rlvg-wo...
⌛ New Submission Deadline: June 6th, AoE
Find out more here: sites.google.com/view/rlvg-wo...
a video game screen shows mario standing on a pyramid and says world 41 time 334
ALT: a video game screen shows mario standing on a pyramid and says world 41 time 334
media.tenor.com
May 31, 2025 at 8:06 PM
“A delayed paper is eventually good; a bad paper is forever bad”
- Shigeru Miyamoto
One more week to submit to our amazing RL and video games workshop!
- Shigeru Miyamoto
One more week to submit to our amazing RL and video games workshop!
Reposted by Miguel Vasco
‼️ Two days left to submit your contributions for our workshop!
Working on RL and video games? Join us! We will have amazing speakers, cool events and a 🎮special topical🎮 best paper award prize!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
Working on RL and video games? Join us! We will have amazing speakers, cool events and a 🎮special topical🎮 best paper award prize!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
a video game shows a checkered floor and a few players
ALT: a video game shows a checkered floor and a few players
media.tenor.com
May 28, 2025 at 8:23 AM
‼️ Two days left to submit your contributions for our workshop!
Working on RL and video games? Join us! We will have amazing speakers, cool events and a 🎮special topical🎮 best paper award prize!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
Working on RL and video games? Join us! We will have amazing speakers, cool events and a 🎮special topical🎮 best paper award prize!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
Fantastic work on general utility MDPs by @pedrosantospps.bsky.social!
You can find a summary of the paper in his account (go follow him as well!).
You can find a summary of the paper in his account (go follow him as well!).
📖 New GAIPS paper on @icmlconf.bsky.social 2025, from @pedrosantospps.bsky.social, Alberto Sardinha and Francisco S. Melo!
📰 “The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes”
📰 “The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes”
May 27, 2025 at 3:03 PM
Fantastic work on general utility MDPs by @pedrosantospps.bsky.social!
You can find a summary of the paper in his account (go follow him as well!).
You can find a summary of the paper in his account (go follow him as well!).
Reposted by Miguel Vasco
One week left to submit your contributions for our workshop! ⏰🎮
We welcome submissions on video games to benchmark open problems in RL and in applications of RL for video game development!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
We welcome submissions on video games to benchmark open problems in RL and in applications of RL for video game development!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
a couple of cartoon characters standing next to each other in a desert .
ALT: a couple of cartoon characters standing next to each other in a desert .
media.tenor.com
May 23, 2025 at 1:48 PM
One week left to submit your contributions for our workshop! ⏰🎮
We welcome submissions on video games to benchmark open problems in RL and in applications of RL for video game development!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
We welcome submissions on video games to benchmark open problems in RL and in applications of RL for video game development!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
Reposted by Miguel Vasco
Running out of time to submit your contributions for our workshop!
We welcome submissions on video games to benchmark open problems in RL and in applications of RL for video game development!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
We welcome submissions on video games to benchmark open problems in RL and in applications of RL for video game development!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
sonic the hedgehog is standing in front of a waterfall in a video game scene .
ALT: sonic the hedgehog is standing in front of a waterfall in a video game scene .
media.tenor.com
May 13, 2025 at 7:46 AM
Running out of time to submit your contributions for our workshop!
We welcome submissions on video games to benchmark open problems in RL and in applications of RL for video game development!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
We welcome submissions on video games to benchmark open problems in RL and in applications of RL for video game development!
⌛ Paper Submission Deadline: May 30th
Find out more here: sites.google.com/view/rlvg-wo...
Reposted by Miguel Vasco
Happy to share that our paper "The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes" got accepted as a spotlight poster at the International Conference on Machine Learning (ICML).
May 3, 2025 at 8:34 AM
Happy to share that our paper "The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes" got accepted as a spotlight poster at the International Conference on Machine Learning (ICML).
Reposted by Miguel Vasco
🎉Excited to share that our paper "𝐇𝐮𝐦𝐚𝐧-𝐀𝐥𝐢𝐠𝐧𝐞𝐝 𝐈𝐦𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥𝐬 𝐈𝐦𝐩𝐫𝐨𝐯𝐞 𝐕𝐢𝐬𝐮𝐚𝐥 𝐃𝐞𝐜𝐨𝐝𝐢𝐧𝐠 𝐟𝐫𝐨𝐦 𝐭𝐡𝐞 𝐁𝐫𝐚𝐢𝐧" has been accepted to #ICML2025!
🔗 Preprint Link: arxiv.org/abs/2502.03081
Huge thanks to my co-authors!
🔗 Preprint Link: arxiv.org/abs/2502.03081
Huge thanks to my co-authors!
Human-Aligned Image Models Improve Visual Decoding from the Brain
Decoding visual images from brain activity has significant potential for advancing brain-computer interaction and enhancing the understanding of human perception. Recent approaches align the represent...
arxiv.org
May 2, 2025 at 9:23 AM
🎉Excited to share that our paper "𝐇𝐮𝐦𝐚𝐧-𝐀𝐥𝐢𝐠𝐧𝐞𝐝 𝐈𝐦𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥𝐬 𝐈𝐦𝐩𝐫𝐨𝐯𝐞 𝐕𝐢𝐬𝐮𝐚𝐥 𝐃𝐞𝐜𝐨𝐝𝐢𝐧𝐠 𝐟𝐫𝐨𝐦 𝐭𝐡𝐞 𝐁𝐫𝐚𝐢𝐧" has been accepted to #ICML2025!
🔗 Preprint Link: arxiv.org/abs/2502.03081
Huge thanks to my co-authors!
🔗 Preprint Link: arxiv.org/abs/2502.03081
Huge thanks to my co-authors!
Reposted by Miguel Vasco
This year I am co-organizing the 8th iteration of the Tractable Probabilistic Modeling #TPM workshop at #UAI2025 🌴 Rio de Janeiro edition 🌴
🌐 lnkd.in/dDK8T5Au
⏰ Submission deadline: May 23th AoE
🌴 Date: July 15th
🧵👇
🌐 lnkd.in/dDK8T5Au
⏰ Submission deadline: May 23th AoE
🌴 Date: July 15th
🧵👇
April 30, 2025 at 10:54 AM
This year I am co-organizing the 8th iteration of the Tractable Probabilistic Modeling #TPM workshop at #UAI2025 🌴 Rio de Janeiro edition 🌴
🌐 lnkd.in/dDK8T5Au
⏰ Submission deadline: May 23th AoE
🌴 Date: July 15th
🧵👇
🌐 lnkd.in/dDK8T5Au
⏰ Submission deadline: May 23th AoE
🌴 Date: July 15th
🧵👇
Reposted by Miguel Vasco
Join us at the Reinforcement Learning Conference 2025 for a Workshop on Reinforcement Learning and Video Games, celebrating a decade since the Atari Nature paper 🎮 🕹️
Check out our webpage for more information: sites.google.com/view/rlvg-wo...
Check out our webpage for more information: sites.google.com/view/rlvg-wo...
April 15, 2025 at 4:08 PM
Join us at the Reinforcement Learning Conference 2025 for a Workshop on Reinforcement Learning and Video Games, celebrating a decade since the Atari Nature paper 🎮 🕹️
Check out our webpage for more information: sites.google.com/view/rlvg-wo...
Check out our webpage for more information: sites.google.com/view/rlvg-wo...
It’s been 10 years since the Atari DQN Nature paper! What better way to celebrate this milestone than with a dedicated workshop on RL and Video Games at @rl-conference.bsky.social? 🎮🎮
Join us to discuss how video games can be used to address fundamental RL problems and how RL can be used in Games!
Join us to discuss how video games can be used to address fundamental RL problems and how RL can be used in Games!
👾👾 We are happy to announce the first Reinforcement Learning and Video Games (RLVG) Workshop at @rl-conference.bsky.social 2025! 🎮🎮
For more information and the call for papers: sites.google.com/view/rlvg-wo...
More details coming soon!
For more information and the call for papers: sites.google.com/view/rlvg-wo...
More details coming soon!
April 15, 2025 at 11:28 AM
It’s been 10 years since the Atari DQN Nature paper! What better way to celebrate this milestone than with a dedicated workshop on RL and Video Games at @rl-conference.bsky.social? 🎮🎮
Join us to discuss how video games can be used to address fundamental RL problems and how RL can be used in Games!
Join us to discuss how video games can be used to address fundamental RL problems and how RL can be used in Games!
The reply-all button should be banned.
Especially when organization-wide mailing lists are in CC.
Rant over.
Especially when organization-wide mailing lists are in CC.
Rant over.
April 14, 2025 at 1:20 PM
The reply-all button should be banned.
Especially when organization-wide mailing lists are in CC.
Rant over.
Especially when organization-wide mailing lists are in CC.
Rant over.
The acknowledgement check for ICML reviews is a bit like global warming.
We see it, we promise we will change, but, in the end, nothing happens.
We see it, we promise we will change, but, in the end, nothing happens.
April 3, 2025 at 3:52 PM
The acknowledgement check for ICML reviews is a bit like global warming.
We see it, we promise we will change, but, in the end, nothing happens.
We see it, we promise we will change, but, in the end, nothing happens.
So happy to finally see @kthuniversity.bsky.social in Bluesky!
Hope more European universities follow suit and expand their academic and research presence here.
Hope more European universities follow suit and expand their academic and research presence here.
March 18, 2025 at 8:49 AM
So happy to finally see @kthuniversity.bsky.social in Bluesky!
Hope more European universities follow suit and expand their academic and research presence here.
Hope more European universities follow suit and expand their academic and research presence here.
Today is a historical day for the RL community (another one!).
Congratulations to Andrew and Rich! Well deserved!
awards.acm.org/about/2024-t...
Congratulations to Andrew and Rich! Well deserved!
awards.acm.org/about/2024-t...
Andrew Barto and Richard Sutton are the recipients of the 2024 ACM A.M. Turing Award for developing the conceptual and algorithmic foundations of reinforcement learning.
Andrew Barto and Richard Sutton as the recipients of the 2024 ACM A.M. Turing Award for developing the conceptual and algorithmic foundations of reinforcement learning. In a series of papers beginning...
awards.acm.org
March 5, 2025 at 2:47 PM
Today is a historical day for the RL community (another one!).
Congratulations to Andrew and Rich! Well deserved!
awards.acm.org/about/2024-t...
Congratulations to Andrew and Rich! Well deserved!
awards.acm.org/about/2024-t...
Reposted by Miguel Vasco
Some extra motivation for those of you in RLC deadline mode: our line-up of keynote speakers -- as all accepted papers get a talk, they may attend yours!
@rl-conference.bsky.social
@rl-conference.bsky.social
February 24, 2025 at 11:16 AM
Some extra motivation for those of you in RLC deadline mode: our line-up of keynote speakers -- as all accepted papers get a talk, they may attend yours!
@rl-conference.bsky.social
@rl-conference.bsky.social