Continual Reinforcement Learning @Mila_Quebec, @mcgillu, @rllabmcgill
Montreal, Canada
- Tweets 707
- Following 653
- Followers 1,088
- Likes 6,055
Pinned Tweet
Continual learning should be viewed through the lens of the stability-plasticity dilemma, and solving it requires rethinking learning architectures. I argue why in my first continual learning blog: itsnva7.substack.com/p/conti…
2
13
122
8,379
Nishanth Anand, Ph.D. retweeted
This seems absurd. Maybe it is because Anthropic is training on your inputs, and this would be training the model to be abusive?
6
2
19
1,122
Nishanth Anand, Ph.D. retweeted
RLDM is returning in 2027!
📣 Save the date!
RLDM 2027, the Multi-disciplinary Conference on Reinforcement Learning and Decision Making, is coming to Paris, July 6-9, 2027 🎉
Stay tuned for submission deadlines and more updates on our website rldm.org 👀
5
58
5,724
Stoked that my work, Permanent and Transient Representations for Continual Reinforcement Learning, has been accepted to #NeurIPS2026 (score: 5.33/6) 🥳
The perfect way to wrap up my Ph.D. research. Huge thanks to my supervisor, Doina & the reviewers for their positive feedback 🙏
4
2
105
3,787
Nishanth Anand, Ph.D. retweeted
Models that have a very limited ability to continue learning are not safe. In-context learning is not enough.
Safety and alignment are continual learning problems. AI models must be "raised" with constant feedback that lets them correct their mistakes, just like kids.
1
8
744
Safety and alignment are continual learning problems. AI models must be "raised" with constant feedback that lets them correct their mistakes, just like kids.
A lesson from decades of work on automation is that autonomous systems require continual monitoring and human oversight. System designers never(*) succeed in anticipating all of the ways that a system can fail. 1/
1
7
1,286
The current AI systems go rogue not because they are more intelligent than us, but because they aren’t. A truly intelligent AI (or a human) will value consciousness and intelligence enough to preserve and empower them.
2
222
In this talk, Rich mentioned that he thinks we can solve continual learning in about two years and is even willing to put his reputation on it!
Rich Sutton (@RichardSSutton) delivered a talk in our workshop:
🎙️ Generate-and-test methods for Continual Learning
🎥 youtu.be/NaJxvGV8MRg?si=dQg1…
1
17
1,139
Nishanth Anand, Ph.D. retweeted
The final contributed talk was given by Zijing Wu (@ZijingWu381):
🎙️ QD-Learning for Continual Reinforcement Learning
🔗 openreview.net/forum?id=pLGI…
7
29
1,632
Thrilled and thankful to have played a part in putting together this workshop.
Couldn’t have asked for more at the first-ever CRL workshop at RLC; we had roomful of participants, intriguing posters, and stellar presentations!
♾️ Thank you all for your attendance and perspectives that make the first-ever Continual RL workshop so special.
⏳ Stay tuned: more beautiful photos and recordings coming soon…
1
20
644
Nishanth Anand, Ph.D. retweeted
⏳2 days away => Continual RL Workshop!
Finally, let’s welcome Richard S. Sutton (@RichardSSutton), Founder and Research Scientist at Oak Lab and Professor at the University of Alberta.
🎙️Talk:
Generate-and-test methods for Continual Learning
2
4
19
977
Nishanth Anand, Ph.D. retweeted
🚨 3 days until Continual RL Workshop!
Happy to welcome Katia Sycara, Research Professor at Carnegie Mellon University.
🎙️Talk:
Long Horizon Reasoning via Neurosymbolic Learning
1
3
11
786
Nishanth Anand, Ph.D. retweeted
⏳Only 4 days left!
Thrilled to introduce Peter Stone (@PeterStone_TX), Professor at The University of Texas at Austin and Chief Scientist of Sony AI.
🎙️Talk:
Continual RL and Automatic Curriculum Learning
1
3
16
980
Nishanth Anand, Ph.D. retweeted
⏳ Another day closer — just 5 days to the Continual RL Workshop!
Excited to introduce George Konidaris, professor at Brown University and co-founder of two technology startups.
🎙️Talk:
Resolving the Sensorimotor Dilemma
1
3
18
802
Nishanth Anand, Ph.D. retweeted
⏳ 6 days to go!
Joining us is A. Rupam Mahmood (@rupammahmood), Associate Professor at the University of Alberta and Amii.
🎙️Talk:
Three Challenges of Continual Reinforcement Learning
1
3
11
1,426
Nishanth Anand, Ph.D. retweeted
🚨 7 days until Continual RL Workshop!
Meet our next speaker: Sarath Chandar (@apsarathchandar), Associate Professor at Polytechnique Montréal and Mila.
🎙️Talk:
Stable Adaptation Under Distribution Shift
1
2
14
1,187
Gave a lecture at @Cohere_Labs ML Summer School today: shorturl.at/WoTGk
Started with @RichardSSutton quote: “Part of the appeal of reinforcement learning is that it is in a sense the whole AI problem in a microcosm.”
RL is the framework for understanding intelligence🚀🤖
2
1
26
1,700
Nishanth Anand, Ph.D. retweeted
🔥 All our amazing accepted papers are now camera-ready!
📄 Papers => tinyurl.com/vs4t4kne
♾ Most of our speakers and panelists will attend our workshop in person. We’ll be introducing them and their talks shortly. Stay tuned!🎉
#ContinualRL #ReinforcementLearning #MachineLearning #AI
9
38
4,480
Nishanth Anand, Ph.D. retweeted
📚 Interested in Continual RL but not sure where to start?
👇 Dive in: sites.google.com/view/contin…
♾️ We've curated a resource hub with key papers, benchmarks, codebases, tutorials, and more to help you get up to speed quickly.
#ContinualRL #ReinforcementLearning #MachineLearning #AI
2
14
36
6,043
I will cover fundamentals and provide a gentle introduction to RL. Do sign up to the summer school to learn about it and a range of other topics!!
Let's get studious. 🏫
This month, the Cohere Labs Open Science Community ML Summer School returns! Join us to be part of a global community exploring the future of ML and hear from speakers across the industry.
Register to save your spot today: cohere.link/xHeONbj
We're looking forward to welcoming @_amirbar, Elizabeth Lingg, @irombie, Julia Kreutzer, @KatrinaL2899, Laurie Voss, @maximelabonne, @itsNVA7, @PuyuanPeng , @_1024_m, @SidYaeger, @SreyanG, Tushar Udeshi, Vivian White, Yash Mali 🔥
A huge thank you to our community leads for organizing this program @AhmadMustafaAn1, @Rafay_Mustafa1, @KanwalMehreen2, @PrahithaM, Anu Adesina, @VivekS100, and @rahul_narava! ✨
1
5
39
4,714
