Star Wars Adventures: Ghosts of Vader's Castle is a 5-issue comic miniseries from IDW Publishing.
.
.
.
#StarWars #DarthVader #VadersCastle #AnakinSkywalker #padmeamidala #C3PO #R3D2 #Vader
.
.
.
#StarWars #DarthVader #VadersCastle #AnakinSkywalker #padmeamidala #C3PO #R3D2 #Vader
September 22, 2025 at 6:30 AM
Star Wars Adventures: Ghosts of Vader's Castle is a 5-issue comic miniseries from IDW Publishing.
.
.
.
#StarWars #DarthVader #VadersCastle #AnakinSkywalker #padmeamidala #C3PO #R3D2 #Vader
.
.
.
#StarWars #DarthVader #VadersCastle #AnakinSkywalker #padmeamidala #C3PO #R3D2 #Vader
Can better architectures & representations make self-play enough for zero-shot coordination? 🤔
We explore this in our ICLR 2025 paper: A Generalist Hanabi Agent. We develop R3D2, the first agent to master all Hanabi settings and generalize to novel partners! 🚀 #ICLR2025 1/n
We explore this in our ICLR 2025 paper: A Generalist Hanabi Agent. We develop R3D2, the first agent to master all Hanabi settings and generalize to novel partners! 🚀 #ICLR2025 1/n
April 4, 2025 at 5:12 PM
Can better architectures & representations make self-play enough for zero-shot coordination? 🤔
We explore this in our ICLR 2025 paper: A Generalist Hanabi Agent. We develop R3D2, the first agent to master all Hanabi settings and generalize to novel partners! 🚀 #ICLR2025 1/n
We explore this in our ICLR 2025 paper: A Generalist Hanabi Agent. We develop R3D2, the first agent to master all Hanabi settings and generalize to novel partners! 🚀 #ICLR2025 1/n
Happy May 4th to all who celebrate
#StarWars #R3D2 #Grogu #C3PO #HanSolo #PrincessLeia #LukeSkywalker #DarthVader
#StarWars #R3D2 #Grogu #C3PO #HanSolo #PrincessLeia #LukeSkywalker #DarthVader
a baby yoda with the words may the 4th be with you
Alt: a baby yoda with the words may the 4th be with you
media.tenor.com
May 4, 2026 at 6:52 AM
Happy May 4th to all who celebrate
#StarWars #R3D2 #Grogu #C3PO #HanSolo #PrincessLeia #LukeSkywalker #DarthVader
#StarWars #R3D2 #Grogu #C3PO #HanSolo #PrincessLeia #LukeSkywalker #DarthVader
Collaborative Multi Agent Reinforcement Learning is key for AI in the future. Check out R3D2, a generalist agent working on text-based Hanabi, accepted at ICLR 2025.
Website: chandar-lab.github.io/R3D2-A-Gener...
Website: chandar-lab.github.io/R3D2-A-Gener...
April 4, 2025 at 5:16 PM
Collaborative Multi Agent Reinforcement Learning is key for AI in the future. Check out R3D2, a generalist agent working on text-based Hanabi, accepted at ICLR 2025.
Website: chandar-lab.github.io/R3D2-A-Gener...
Website: chandar-lab.github.io/R3D2-A-Gener...
This guy gives a great example of the subtle brilliance at work. (if timestamp doesn't work, go to exactly 10:00 in)
www.youtube.com/watch?v=r3D2...
www.youtube.com/watch?v=r3D2...
Pearl Jam Drummers
YouTube video by Adam Sivitz
www.youtube.com
July 8, 2025 at 12:11 AM
This guy gives a great example of the subtle brilliance at work. (if timestamp doesn't work, go to exactly 10:00 in)
www.youtube.com/watch?v=r3D2...
www.youtube.com/watch?v=r3D2...
June 16, 2026 at 4:19 AM
Excited to share our ICLR 2025 paper: A Generalist Hanabi Agent!🎇
R3D2 agent plays all Hanabi settings at once and coordinates zero-shot with novel partners (Something SOTA LLMs can't do)—powered by flexible architecture that handle changing obs/action spaces. 🧵👇
R3D2 agent plays all Hanabi settings at once and coordinates zero-shot with novel partners (Something SOTA LLMs can't do)—powered by flexible architecture that handle changing obs/action spaces. 🧵👇
Can better architectures & representations make self-play enough for zero-shot coordination? 🤔
We explore this in our ICLR 2025 paper: A Generalist Hanabi Agent. We develop R3D2, the first agent to master all Hanabi settings and generalize to novel partners! 🚀 #ICLR2025 1/n
We explore this in our ICLR 2025 paper: A Generalist Hanabi Agent. We develop R3D2, the first agent to master all Hanabi settings and generalize to novel partners! 🚀 #ICLR2025 1/n
April 4, 2025 at 5:15 PM
Excited to share our ICLR 2025 paper: A Generalist Hanabi Agent!🎇
R3D2 agent plays all Hanabi settings at once and coordinates zero-shot with novel partners (Something SOTA LLMs can't do)—powered by flexible architecture that handle changing obs/action spaces. 🧵👇
R3D2 agent plays all Hanabi settings at once and coordinates zero-shot with novel partners (Something SOTA LLMs can't do)—powered by flexible architecture that handle changing obs/action spaces. 🧵👇
⚡Zero-Shot Coordination: R3D2 can be trained on multiple settings at once (e.g., 2p & 3p), using simpler games to boost learning in complex ones—letting it coordinate across unseen game settings and partners without explicit training on those settings! 4/n
April 4, 2025 at 5:12 PM
⚡Zero-Shot Coordination: R3D2 can be trained on multiple settings at once (e.g., 2p & 3p), using simpler games to boost learning in complex ones—letting it coordinate across unseen game settings and partners without explicit training on those settings! 4/n
🤝 This was a project led by my students Arjun and
Hadi, in collaboration with Mathieu, Miao, and Janarthanan!
Paper: arxiv.org/abs/2503.14555
Code: github.com/chandar-lab/...
Models: huggingface.co/chandar-lab/...
Website: chandar-lab.github.io/R3D2-A-Gener.... 7/7
Hadi, in collaboration with Mathieu, Miao, and Janarthanan!
Paper: arxiv.org/abs/2503.14555
Code: github.com/chandar-lab/...
Models: huggingface.co/chandar-lab/...
Website: chandar-lab.github.io/R3D2-A-Gener.... 7/7
A Generalist Hanabi Agent
Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these systems are unable to perform well on any other setting t...
arxiv.org
April 4, 2025 at 5:12 PM
🤝 This was a project led by my students Arjun and
Hadi, in collaboration with Mathieu, Miao, and Janarthanan!
Paper: arxiv.org/abs/2503.14555
Code: github.com/chandar-lab/...
Models: huggingface.co/chandar-lab/...
Website: chandar-lab.github.io/R3D2-A-Gener.... 7/7
Hadi, in collaboration with Mathieu, Miao, and Janarthanan!
Paper: arxiv.org/abs/2503.14555
Code: github.com/chandar-lab/...
Models: huggingface.co/chandar-lab/...
Website: chandar-lab.github.io/R3D2-A-Gener.... 7/7
$\href{https://github.com/chandar-lab/R3D2-A-Generalist-Hanabi-Agent}{R3D2-A-Generalist-Hanabi-Agent}$ [7/7 of https://arxiv.org/abs/2503.14555v1]
March 20, 2025 at 5:58 AM
to work with unfamiliar partners or situations. In this paper, we introduce Recurrent Replay Relevance Distributed DQN (R3D2), a generalist agent for Hanabi, designed to overcome these limitations. We reformulate the task using text, as language has [4/7 of https://arxiv.org/abs/2503.14555v1]
March 20, 2025 at 5:57 AM
to work with unfamiliar partners or situations. In this paper, we introduce Recurrent Replay Relevance Distributed DQN (R3D2), a generalist agent for Hanabi, designed to overcome these limitations. We reformulate the task using text, as language has [4/7 of https://arxiv.org/abs/2503.14555v1]
Méga Dossier : R3D2 : des bornes d’arcade pour redonner le sourire à l’hôpital megaforcemagazine.com/2025/11/mega...
Méga Dossier : R3D2 : des bornes d’arcade pour redonner le sourire à l’hôpital - Méga Force2025
R3D2, c’est l’histoire d’une bande de passionnés qui ont décidé d’allier jeux vidéo, solidarité et écologie pour faire sourire les enfants à l’hôpital.
megaforcemagazine.com
November 9, 2025 at 6:31 PM
Méga Dossier : R3D2 : des bornes d’arcade pour redonner le sourire à l’hôpital megaforcemagazine.com/2025/11/mega...
R3D2 and BB-9 race towards the starships for the finish line. BB-9 is falling back in a dramatic 6 feet gap behind R3D2. “They don’t make’em like they used to. It’s really hard to tell who’s going to win this race, Jim?” #greetingcardart, #starwars, #penart, #cardart, #sharpieart
December 23, 2025 at 7:12 PM
R3D2 and BB-9 race towards the starships for the finish line. BB-9 is falling back in a dramatic 6 feet gap behind R3D2. “They don’t make’em like they used to. It’s really hard to tell who’s going to win this race, Jim?” #greetingcardart, #starwars, #penart, #cardart, #sharpieart
William Ljungbergh, Bernardo Taveira, Wenzhao Zheng, Adam Tonderski, Chensheng Peng, Fredrik Kahl, Christoffer Petersson, Michael Felsberg, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
https://arxiv.org/abs/2506.07826
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
https://arxiv.org/abs/2506.07826
June 10, 2025 at 8:42 AM
William Ljungbergh, Bernardo Taveira, Wenzhao Zheng, Adam Tonderski, Chensheng Peng, Fredrik Kahl, Christoffer Petersson, Michael Felsberg, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
https://arxiv.org/abs/2506.07826
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
https://arxiv.org/abs/2506.07826
🎭 Robustness in Cross-Play: We introduce a new inter-setting eval alongside inter/intra-algorithm cross-play—R3D2 adapts smoothly to new agents & envs, outperforming others. Even our 12 (!) reviewers liked the thorough eval! 🔍 #CrossPlay
Openreview: openreview.net/forum?id=pCj...
5/n
Openreview: openreview.net/forum?id=pCj...
5/n
openreview.net
April 4, 2025 at 5:12 PM
🎭 Robustness in Cross-Play: We introduce a new inter-setting eval alongside inter/intra-algorithm cross-play—R3D2 adapts smoothly to new agents & envs, outperforming others. Even our 12 (!) reviewers liked the thorough eval! 🔍 #CrossPlay
Openreview: openreview.net/forum?id=pCj...
5/n
Openreview: openreview.net/forum?id=pCj...
5/n
🔄 Self-Play & Generalization: R3D2 adapts to new partners & game setups without complex MARL tricks—just smart representations & architecture. Shows self-play alone can go far for generalizable policies! #ZeroShot #PolicyTransfer 3/n
April 4, 2025 at 5:12 PM
🔄 Self-Play & Generalization: R3D2 adapts to new partners & game setups without complex MARL tricks—just smart representations & architecture. Shows self-play alone can go far for generalizable policies! #ZeroShot #PolicyTransfer 3/n
🔡 Dynamic observation- and action-space: We frame Hanabi as a text game and use a dynamic action-space architecture, DRRN (He et al., 2015), letting R3D2 adapt across settings via text input—drawing on the power of language as representation. #TextGames 2/n
April 4, 2025 at 5:12 PM
🔡 Dynamic observation- and action-space: We frame Hanabi as a text game and use a dynamic action-space architecture, DRRN (He et al., 2015), letting R3D2 adapt across settings via text input—drawing on the power of language as representation. #TextGames 2/n
