Goal: Understanding the computational and statistical principles required to design adaptive agents. Associate Prof @polymtl @Mila_Quebec 🇨🇦 #MahsaAmini
Montreal, Quebec, Canada
- Tweets 5,811
- Following 1,632
- Followers 5,879
- Likes 5,668
If you're a professor or a student in STEM in a Western country, you probably know someone from the Sharif University of Technology in Iran. They might have be your students, peers, or friends.
That university is now under attack by the Islamic Republic.
🧵(1/16)
#MahsaAmini
139
3,587
7,442
The news and videos are just coming out. I will post a few here.
We see students being trapped in a parking lot at the university, escaping from those who appear to be paramilitary.
nitter.app/MAminGeek/status/15765…
(2/16)
#IranProtests #SharifUniversity
Amin Alam
4
208
596
I am teaching a course on Reinforcement Learning!
I cover fundamental concepts and algorithms and often prove why they work.
All the slides, lecture notes, and videos are available here: amfarahmand.github.io/IntroR…
The YouTube channel for the course is piped.video/playlist?list=PL…
6
115
612
We also hear something that sounds like gunshots.
nitter.app/pouriazeraati/status/1…
(3/16)
#MahsaAmini #Sharif
Pouria Zeraati
2
135
462
A new book on LLMs: Foundations of Large Language Models by Tong Xiao and Jingbo Zhu.
arxiv.org/abs/2501.09223
Covers topics such as pretraining, scaling laws, in-context learning, COT, RLHF, etc.
Haven't read it yet, but having a single doc covering all these can be convenient.
4
83
508
33,334
We see the police shooting paintball at a passerby who is trying to record the police taking away a detained student.
nitter.app/1500tasvir/status/1576…
(4/16)
#MahsaAmini
#Sharif
2
136
431
What I am sure about is that Iran and the mental model of most Iranians have permanently changed. There is no going back.
(16/16)
#MahsaAmini
7
76
385
This all started about two weeks ago when the "morality" police of the Islamic Republic murdered a young woman named #MahsaAmini.
I've written about it before to provide some context.
nitter.app/SoloGen/status/1571560…
By now, you can find about the issue on mainstream media too.
(5/16)
A few days ago, the morality policy of the Islamic Republic of Iran murdered a 22 year woman called #Mahsa_Amini. You can see in this video how cruely they treat women (not Mahsa).
Trigger Warning: Watching this is upsetting.
1
87
367
Mahsa's death has a Butterfly effect. Iranians have since protested in Iran and all over the world almost everyday. There was a demonstration of 50K in #Toronto on October 1st. And it wasn't just in Toronto. 150 other cities around the world joined as well!
(7/16)
#MahsaAmini
2
72
356
Since the murder of #MahsaAmini, Iran has permanently changed. Not that it was the first time such a crime has happened. But this time is just different.
(6/16)
2
71
362
This is not the first time that the IR has violently suppressed Iranians. Its foundation is based on suppression of people and their liberty. It has happened too many times for me to report.
(8/16)
1
59
284
Within a university, my memory goes back to July 1999, when they attacked the University of Tehran, killed several students and arrested 1000+.
en.wikipedia.org/wiki/Iran_s…
(9/16)
#SharifUniversity
2
57
279
If you have read the novel 1984 by George Orwell, that should give you an idea of how such a government works.
Sometimes I wonder whether they have actually used that novel as the blueprint of how to govern. Or maybe all authoritarian governments tend to be alike?
(13/16)
3
52
279
Going back to today: Raiding a university will probably not be limited to #SharifUniversity. This will happen at other universities too, if not already. They are afraid of anyone who thinks and rebels against their indoctrination.
(12/16)
2
56
266
The 1999 invasion of the university started a new era of resistance, and unfortunately also a consequent depression for a generation of students.
(10/16)
1
51
258
Those students started hopeful of then President Khatami (1997-2005) and the Reformists movement, but got disappointed a few years later when much of their hopes and wishes didn't come to a fruition.
The realization for many was simple: IR is not reformable.
(11/16)
#MahsaAmini
1
52
252
I don't know what will happen to Iran in the near future. The IR might start a bloodbath as a temporarily Band-aid to save themselves.
I am convinced that the top officials will not hesitate to do so. Think of extremist psychopaths with political and military power.
(14/16)
2
48
247
The mid-rank government officials or military might be another story. They may evaluate what they are doing and decide to do otherwise, either due to their awakened conscience or a reevaluation of their own utility.
(15/16)
#IranProtests2022
1
47
235
Bonjour-Hi!
1) We moved to Montreál! It is good to be back and lovely so far.
2) I joined the Department of Computer and Software Engineering of the Polytechnique Montréal @polymtl as an associate professor and Mila @Mila_Quebec as the core academic member. 🇨🇦
More news to come!
22
7
240
13,807
I plan to recruit one or two graduate students in #ReinforcementLearning this year. If you are interested, apply through @UofTCompSci @UofT and mention my name in your application (deadline: Dec 1).
2
51
178
🎉Good news, everyone! 🎉
I will recruit graduate students on the algorithmic and theoretical aspects of Reinforcement Learning.
You will join Adage, @Mila_Quebec, and @polymtl.
More info on why and how you should apply:
academic.sologen.net/2024/11…
Deadline: Dec 1st
ALT The unofficial logo of the Adaptive Agents Lab (Adage). It shows a cylindrical robot with some gauges and buttons on it.
1
38
181
17,544
If you are interested in graduate studies on reinforcement learning, consider applying to the Department of Computer Science, University of Toronto and work with me.
6
59
176
I am happy to be named a Canada CIFAR AI Chair and grateful for the support of CIFAR @CIFAR_News.
As part of the Pan-Canadian AI Strategy, we are announcing an expansion of the Canada CIFAR AI Chairs program, bringing the total number of chairs to 46, from 29 announced last December.
Meet Canada’s AI leaders:
cifar.ca/spring-2019-ai-chai…
#CIFARAI
33
9
162
My PhD students are interesting in doing research internship next summer, so I thought I should advertise them here, in case you are hiring.
They have a solid foundation in #ReinforcementLearning and #MachineLearning.
Contact them directly, or DM.
Please RT!
4
26
147
A few more lectures on RL are recorded. I am going to gradually post them here.
All material are available here:
amfarahmand.github.io/IntroR…
1
14
137
"Without a perfect model, model-based RL is hopeless!"
Our paper at #ICLR2024 challenges this belief! Even an inaccurate model can help a lot. Don’t throw it away!
Title: Maximum Entropy Model Correction in Reinforcement Learning
Paper: openreview.net/forum?id=kNpS… 🧵(1/7)
ALT The figure compares the return of three RL approaches. QLearning (a model-free RL algorithm), Dyna (a model-based RL algorithm), and Model Correcting Dyna (the new approach). Model Correcting Dyna performs better than the rest, achieving higher returns faster than QLearning. Dyna cannot reach the maximum return.
4
19
136
12,946
Good blog post, by Nicolas Carlini, on how LLMs can boost your performance (if you don't already know):
nicholas.carlini.com/writing…
1
17
135
18,461
Why do we hold #NeurIPS2022 in a closed-bordered country such as the USA? This greatly impacts many researchers with less privileged citizenships.
@NeurIPSConf
I think this is a good time as any to remind people that many students from India (and many other countries) with accepted papers to @NeurIPSConf wouldn't be able to present because the US Visa situation is so backed up (the next available appointments are in Mar/April 2024).
4
6
120
I haven't heard the whole talk, so I don't know the exact context, but based on this slide and short recording of a brave person who confronting the speaker, and assuming this is the only time someone's nationality was highlighted, it indeed looks inappropriate to me.(1/6)
1/3 Today, an anecdote shared by an invited speaker at #NeurIPS2024 left many Chinese scholars, myself included, feeling uncomfortable. As a community, I believe we should take a moment to reflect on why such remarks in public discourse can be offensive and harmful.
4
2
125
18,195
This is a very well-thought email! It also helps if your BS and MS were from Cambridge, had internships at MIT, Bernstein, Weizmann, and worked as a quant at Goldman Sachs and as a Product Manager at Google.
"Gentlemen you had my curiosity, but now you have my attention."
Cold emails are hard and good ones can change a life. Here is my email to @NandoDF that started my career in ML (at the time I was a PM at Google) docs.google.com/document/d/1… Real effort (incl feedback) went into drafting it. Thanks to @EugeneVinitsky for nudging me to put it online
3
3
115
18,242
The blame, foremost, goes to Mr. Vuong for not disclosing his past. That was immoral.
But part of the blame goes to the @liberal_party that didn't do the due diligence in background checking of a prospective politician. How many other skeleton are in the closet?
14
9
118
There are many summer internship positions at @VectorInst!
Deadline: Jan 9th.
vectorinstitute.ai/internshi…
If you are interested in working on theoretical/algorithmic aspects of #ReinforcementLearning with me, please apply. I intend to recruit one or two interns.
3
19
120
33,609
Blog: Is Your Neural Network at Risk? The Pitfall of Adaptive Gradient Optimizers
Summary: Models trained using SGD exhibit significantly higher robustness to input perturbations than those trained via adaptive gradient methods such as Adam or RMSProp.
vectorinstitute.ai/is-your-n…
ALT These three figures show the performance of SGD, RMSProp, and Adam across datasets MNIST, SVHN, CIFAR10, CIFAR100, Caltech101, FashionMNIST, and Imagenette. The X axes are accuracy under Gaussian perturbation, l2 attacks, and l_inf attacks. The Y axis is standard test error.
4
20
106
13,593
One of the reasons you see many young Iranians apply to your universities is that they are escaping a “condition”.
A “condition” that arrests those who protest against the deteriorating economy, tortures them to confess, and sentences them to execution.
#StopExecutionsInIran
2
15
107
Goodbye Toronto! ❤️ You will be missed!
(... et amis aussi!)
ALT Toronto during TIFF 2024
7
1
104
16,906
I use Wikipedia everyday, not only for satisfying my curiosity, but also for my research. Yes, I read technical papers and books too, but in many cases Wikipedia is all that I need.
So consider donating to @Wikipedia, if you can!
#iloveWikipedia donate.wikimedia.org/?utm_me…
15
95
I cringe when I see papers using only 2 or 3 runs (i.e., seeds) in reporting their confidence interval or the shaded area around the curves in their figures.
#ReinforcementLearning #DeepLearning #MachineLearning #Experiments
(1/13)
1
12
101
What are some potentially useful, but almost forgotten/ignored, ideas in AI/ML?
#MachineLearning #ArtificialIntelligence #RemembranceofDaysPast
11
22
87
Learning that DeepMind decided to close its Edmonton's office is upsetting. I don't know the detail, but I hope my friends and colleagues aren't unpleasantly affected.
2
84
19,951
If you are soon graduating from a PhD program and want to conduct world-class research in Machine Learning (including DL, RL, CV, NLP, etc), apply to become a Vector Postdoctoral Fellow! @VectorInst
Deadline: March 31st
vectorinstitute.bamboohr.com…
#PostdocPosition
3
24
83
This is concerning!
Ex: If you are from Iran, China, or Lebanon and study AI (or engineering), you cannot study/visit/work at ETH?
Also, it uses "country of origin". Not a lawyer, so correct me, but it *may* mean where you were born, even if you are a citizen of another country.
It has not been reported much, but I believe ETH Zurich has, as of last week, banned new Master and PhD students who attended a long list of universities in China, Russia, and Iran. 🧵
6
4
81
17,723
In your opinion, what is the most interesting area of AI/ML that only a handful of researchers are currently working on?
Asking for a friend! (;
#MachineLearning #FarFromMaddingCrowd
20
10
84
I wish I used this visualization last week in my ML course!
Mutual Information quantifies the dependency of two random variable. It's zero only when the r.v.s are independent. But covariance is only about their linear relation and can be zero even if the r.v.s are dependent.
11
81
Dimitri Bertsekas is the master of dynamic programming and RL. I've learned a lot from his Neuro-dynamic Programming (with J. Tsitsiklis) and Stochastic Optimal Control (with S. Shreve), and more recently the Abstract DP. I keep learning from them and using them in my own course.
11
74
We have several postdoc positions at the Vector Institute. If you are a rising star in #MachineLearning, we want you to be here!
The deadline for this round is June 12th. After this, we have another round in September/October.
vectorinstitute.bamboohr.com…
5
23
70
Tong Zhang has a new book on Learning Theory. I was introduced to it by @CsabaSzepesvari just today, so obviously I haven't read it yet. From a quick skim, it looks promising. Post it for now, so I don't forget.
tongzhang-ml.org/lt-book.htm…
#MachineLearning #Statistics
11
77
8,679
If you are interested in doing a postdoc on #ReinforcementLearning, please apply to @VectorInst Postdoctoral Fellowship Program. I am looking for a theory-inclined person to start from around Summer 2023 or soon after.
Deadline: Feb 28th, 12AM
Please RT!
workforcenow.adp.com/mascsr/…
1
38
72
18,932
Internet is shut off in Iran by the government (I know, it is surreal). Consider this in your grad application deadline. Maybe extend it for those applying from Iran.
@UofT @UofTCompSci @uoftmie
@UAlberta @UAlbertaCS
@mcgillu
@SCSatCMU
#IranProtests #Internet4Iranِ
2
21
71
If you are at #NeurIPS2019 and curious to know the relation between distributional reinforcement learning and Fourier space, come to my poster today (Tue) at 10:45 AM, East Exhibition Hall B + C, poster No. 207.
1
4
72
A good measure of diversity of an organization is the diversity of the senior management, high-rank officials, and people in position of power.
The apparent diversity of low-rank workers is probably a better indicator of broad exploitation than diversity.
3
10
72
A difference between an expert and a novice is in their robustness to uncertainty.
Someone who just learned something might understand what they learned very well, but they easily get confused if the presentation of the material slightly changes. Their understanding is fragile.
2
6
73
"Intelligence is the computational part of the ability to predict and control a stream of experience" - Rich Sutton from @UAlberta @AmiiThinks @DeepMind at @VectorInst today.
I like this definition of intelligence (as well as William James and John McCarthy's).
3
12
67
[This applies to Iranians] I am almost convinced that either you are with us or with them. There might have been a grey area 20 years ago where reform and dialogue could be hoped, but no more: it is Black or White now!
#MahsaAmini #OpIran
2
13
62
Call it by its name: an RL architecture -- the cherry on top of the cake! 😉
BTW, the concept of World Model isn't new. It's a rebranding of the model in model-based RL (early 90s) and even earlier in Self-Tuning Regulators in adaptive control (early 70s).
#ReinforcementLearning
Chief AI Scientist Yann LeCun (@ylecun) is sketching an alternate vision for building human-level AI. LeCun proposes that the ability to learn “world models” — internal models of how the world works — may be the key. Learn more: ow.ly/I5rR50I1KKl
2
6
59
"A course per emerging topic such as RL would be a good start."
RL as an emerging field?🤔🙄
The unfortunate truth is that many prominent universities don't offer any RL course. They don't have any PI focusing on RL. The sad truth is that this is sometimes a political decision.
6
2
62
10,802
Like most sentient beings, I get stressed about the fast pace of machine learning research and the sheer volume of papers, which suffuse all my feeds.
To be far from this madding crowd, I visited a local math department’s library.
1
63
My plan for August was to write three chapters of a book.
September starts, and I don’t even have an outline.
Well … it would be fun next few months!
3
63
Preventing ordinary Iranians from being involved in scientific activies because of their country of origin/residence is disheartening and discriminatory, no matter how legally justifiable it is.
I am really sad that @neuromatch had to kick out all the Iranian students and TAs from it academy due to US sanctions! Politics should not be a barrier against scientific exchange and collaboration. Maybe they shouldn’t have registered it in a country with such crazy laws!
1
5
61
Happy Nowruz/Spring/Persian New Year 1403!
#Nowruz
1
1
59
2,299
I feel shocked, sad, and sorry for my Afghan sisters and brothers who will live under the oppressive regime of Taliban. It is very scary to live under the regime following the 1400 year-old raw and literal interpretation of Islamic sharia.
#Afghanistan
1
57
The challenge of work-life balance is a false dichotomy to begin with. Work is not something outside life. It is a part of life itself. The real issue is about life-life balance.
6
2
60
The first Nobel prize for Machine Learning!
Geoffrey Hinton (@geoffreyhinton) and John Hopfield (@HopfieldJohn) just won the Nobel Prize in Physics! Wow! Congratulations! 🍾🎇
2
5
57
3,886
The SARSA algorithm’s name comes from it usages of the State, Action, Reward, next State, and next Action in order to update the action-value function.
Based on this naming convention, the Q-Learning algorithm could be called SARS!
I am glad we don't!
#ReinforcementLearning
4
4
58
If you are an Area Chair for #ICML2023, please send a reminder to the reviewers to participate in discussions.
Reminding worked: there wasn't much reviewer activities the whole week until I sent a reminder last night.
If you are a reviewer, please read the rebuttals and react!
3
5
58
12,561
Happy Norooz (the Iranian New Year) and the Spring equinox!
#Nowruz
58
How the government of Ontario shoots itself in the foot by cutting the funding on #AI research at @VectorInst @CIFAR_News .
@fordnation @ToddSmithPC
Disclaimer: To be clear I am only representing my own opinion here, and not Vector's or CIFAR's.
thestar.com/news/gta/2019/05…
7
9
53
A year ago today Mahsa Amini was killed by the thugs of the Islamic Republic of Iran. She was not the first and has not been the last to be demised by the IR in the past 44 years, but she was the butterfly that fundamentally changed most Iranians.
#MahsaAmini #WomanLifeFreedom
8
49
2,914
I am teaching an Introduction to Machine Learning (grad-level) course this semester, so I thought I would brainstorm with my tweeps.
What topic do you wish was included in your own Intro to ML course that wasn't?
OR
What topic do you think should be included that is often not?
19
4
50
I am glad that our department stands in solidarity with Iranians.
#MahsaAmini #مهسا_امینی
Statement of solidarity with Iranian community members from Eyal de Lara, Professor and Chair, Department of Computer Science.
ALT A statement from Eyal de Lara, Professor and Chair, Department of Computer Science: The Department of Computer Science stands in solidarity with our Iranian community members and everyone impacted by the detainment and death of 22-year-old Mahsa Amini, and subsequent violent crackdowns on protests, including at Tehran’s Sharif University. Many of our students, faculty and staff are graduates of these universities, and we acknowledge that this is an exceptionally challenging time for them, and for all with personal ties to Iran. We join with those who have voiced their outrage at these egregious acts. Institutions of higher education must be safe places for open speech and the free exchange of ideas. Speaking out is more important than ever, as government censorship is used to silence protests and conceal ongoing brutality amid escalating violence across Iran. We also reaffirm our unflinching commitment to women's rights and all human rights.
7
49
I will be at #NeurIPS2018.
If you are interested in reinforcement learning or want to know more about available positions at @VectorInst (research scientist or postdoc), talk to me.
2
2
51
A few days ago, the morality policy of the Islamic Republic of Iran murdered a 22 year woman called #Mahsa_Amini. You can see in this video how cruely they treat women (not Mahsa).
Trigger Warning: Watching this is upsetting.
Do you really want to know how Iranian morality police killed Mahsa Amini 22 year old woman? Watch this video and do not allow anyone to normalize compulsory hijab and morality police.
The Handmaid's Tale by @MargaretAtwood is not a fiction for us Iranian women. It’s a reality.
2
8
47
Great advice, and applicable to other fields of knowledge too.
When reading a paper, I occasionally try to solve their problem before reading their solution. This is very time consuming and I often can't find a good solution, but it opens up my mind.
#DeliberatePractice
How to use the research literature. When approaching a difficult mathematical problem, first think deeply upon it on your own, using all the ideas you can muster, before consulting the work of others. Push your own ideas as hard as you can first, and read only afterward.
1
2
47
Very interesting!
My dream dynamical system to control, however, is the whole body of an Octopus!
I wish I knew more mechanics to model it, though I suspect a bit more wouldn't be enough – it needs a complicated nonlinear PDE, I believe.
Anyone interested?
We are releasing OstrichRL 🎉
The repository contains a musculoskeletal model of an ostrich in MuJoCo, a set of dm_control tasks for reinforcement learning, and motion capture data.
GitHub: github.com/vittorione94/ostr…
Paper: arxiv.org/abs/2112.06061
8
48
I am very excited that I have joined the Vector Institute! I am looking forward to start new collaborations and build a strong research team there.
@VectorInst
We're very excited for you to meet Amir-massoud Farahmand, our newest Faculty Member who specializes in reinforcement learning!
Read what he has to say about his decision to pursue his research @VectorInst in Toronto:
medium.com/@VectorInstitute/…
@SoloGen
piped.video/HzzwiJfeYiI
3
1
45
So sad and unfortunate is #IranPlaneCrash. I am still in shock, and I guess I will be for a while, that how all those lives have perished so suddenly and needlessly.
1
1
45
If you are interested in model-based reinforcement learning (MBRL), you want to read Iterative Value-Aware Model Learning, which is accepted at #NeurIPS2018.
papers.nips.cc/paper/8121-it…
1
7
47
Interesting note by @ccanonne_ on comparing KL vs TV.
We have the Pinsker inequality that says TV(p,q) < sqrt{KL(p||q)} (I am ignoring constants).
The trouble is that the RHS can become larger than one, while the LHS is at most one.
arxiv.org/abs/2202.07198
2
10
43
7,697
RLC 2024 was a fun event, and it is likely to become the top venue for the RL Community. Think of it as ICLR back in ~2014.
Consider submitting your RL papers to this venue.
(Edmonton, Alberta 🇨🇦 is also a beautiful city in the summer.)
#ReinforcementLearning
The call for papers for RLC is now up! Abstract deadline of 2/14, submission deadline of 2/21!
Please help us spread the word.
rl-conference.cc/callforpape…
1
4
48
8,540
Done with all my reviewing and area chairing responsibilities for 2019!
I think I should write about it, especially about the area chairing part. Maybe a blog post in the near future?
1
44
I spend ~4-6h (and sometimes even more) on each conference paper. This means that I have to dedicate most days of a week or two to reviewing for a conference.
I see this as a community service. I also learn those papers relatively well, as an added bonus.
2
1
43
Are you a reviewer who cannot submit your report by the deadline?
Contact your senior program committee. Being a bit late might be OK. AWOL is not.
SPC is wondering whether they should wait for you or find an emergency reviewer. Don't leave them in the dark. Communicate!
5
43
No more excuse not to learn #ReinforcementLearning!
I haven't read it yet, but I am comfortable recommending it knowing that this book is from great researchers who have made significant contributions to RL.
Want to learn / teach RL?
Check out new book draft:
Reinforcement Learning - Foundations
sites.google.com/view/rlfoun…
W/ @shiemannor and @YishayMansour
This is a rigorous first course in RL, based on our teaching at TAU CS and Technion ECE.
41
3,848
Deep Learning and Reinforcement Learning Summer Schools are now accepting applicants. The schools are in Toronto (July 25-August 3), and both have great lineup of speakers.
Apply and spread the news!
The deadline is March 26.
dlrlsummerschool.ca/
3
19
44
You want to design a risk-sensitive model-based #ReinforcementLearning agent. What is the right way to learn the model? MLE? Value-aware?
Tyler Kastner, @MuratAErdogdu, and I investigate this!
Paper: openreview.net/forum?id=SLTQ…
Poster: sologen.net/presentations/Di…
#NeurIPS2023
🧵000/111
1
6
42
4,757
Q: Does assassinating another country’s top general de-escalate the tension in the Middle East?
A: No!
I am worried that many innocent lives would be lost.
2
43
They weren't considered clowns at all! They were all respected researchers. They were even pretty famous, though of course didn't have their current hyper-famous/god-like status.
It's true that (D)NNs weren't mainstream in 2000s, and many were skeptical of their importance.
1
39
Old age has many symptoms. When I was a student, I used to feel delighted if the conference deadlines got extended. Nowadays I get annoyed. “I don’t want to work on this damned thing anymore”.
3
1
43
Dimensionality Reduction for Representing the Knowledge of Probabilistic Models is accepted at #ICLR2019. This is by Marc Law, Jake Snell (@jake_snell), Richard Zemel, Raquel Urtasun, and myself.
openreview.net/forum?id=SygD…
1
3
41
Adaptive Agents Lab (yes, it is us!) had the pleasure of having Pierluca D'Oro @proceduralia this Monday to give a good talk about "Towards an Empirical Science of Neural Networks for Sequential Decision-Making".
#ReinforcementLearning
1/16 🧵
1
3
39
6,013
Intro to RL: Learning from a Stream of Data (Part 2)
Topics:
- SARSA
- Stochastic Approximation
- Convergence proof of Q-Learning (finite MDPs)
Video: piped.video/Pm6MWLCuKak
Slides: amfarahmand.github.io/IntroR… (slides 49+)
LNRL: amfarahmand.github.io/IntroR… (Sec. 4.6+)
3
4
39
I gave a talk @Carleton_U on "Reinforcement Learning for High-Dimensional Problems: From PDE Control to Model Learning" and had a lot of interesting conversations.
Thanks to @KomeiliMJ for hosting me at @CU_DataScience.
3
41
Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning by Richard Sutton, Doina Precup, and Satinder Singh (1999) has recently won the Classic Artificial Intelligence Journal (AIJ) paper award.
sciencedirect.com/science/ar…
1
7
40
Did you know that the optimizer significantly affects the robustness of NN? And Adam is the wrong answer!😯
"Understanding the robustness difference between SGD and adaptive gradient methods” dives deep into this.
Paper: openreview.net/forum?id=ed8S…
Code: github.com/averyma/opt-robus…
🧵1/4
1
8
40
5,464
Submit your work to the Decision Awareness in #ReinforcementLearning Workshop at @icmlconf.
Decision awareness is a design principle: each module of an RL system should be trained to explicitly consider how its interaction with other modules affects the agent's performance.
Happy to announce the Decision Awareness in Reinforcement Learning workshop at @icmlconf!
We welcome contributions until May 27, 2022 AoE
The workshop website: darl-workshop.github.io
Hope to see you in Baltimore or virtually in July!
1/4
2
5
40