Ahana D. (she/her)
@ahana.bsky.social
Reinforcement Learning PhD student, UPF Barcelona.
Uncertain in the face of optimism.
ahanadeb.github.io
Uncertain in the face of optimism.
ahanadeb.github.io
Pinned
Ahana D. (she/her)
@ahana.bsky.social
· Jan 21
Found the coolest note while cleaning out the office, clearly it belongs on the wall :) author unknown
Reposted by Ahana D. (she/her)
✨ The last day kicked off with an amazing talk by @katjahofmann.bsky.social
"World and Human Action Models for Gameplay Ideation" 🎮🤖
Exciting vision from the Game Intelligence team @msftresearch.bsky.social
"World and Human Action Models for Gameplay Ideation" 🎮🤖
Exciting vision from the Game Intelligence team @msftresearch.bsky.social
September 19, 2025 at 11:31 AM
✨ The last day kicked off with an amazing talk by @katjahofmann.bsky.social
"World and Human Action Models for Gameplay Ideation" 🎮🤖
Exciting vision from the Game Intelligence team @msftresearch.bsky.social
"World and Human Action Models for Gameplay Ideation" 🎮🤖
Exciting vision from the Game Intelligence team @msftresearch.bsky.social
Reposted by Ahana D. (she/her)
I am in Vancouver at ICML, and tomorrow I will present our newest paper "Partially Observable Reinforcement Learning with Memory Traces". We argue that eligibility traces are more effective than sliding windows as a memory mechanism for RL in POMDPs. 🧵
July 16, 2025 at 1:35 AM
I am in Vancouver at ICML, and tomorrow I will present our newest paper "Partially Observable Reinforcement Learning with Memory Traces". We argue that eligibility traces are more effective than sliding windows as a memory mechanism for RL in POMDPs. 🧵
Reposted by Ahana D. (she/her)
After all these reports of authors adding language instructions for LLM reviews in their papers I wanted to check this myself and I downloaded the .tex source from one of these papers.
Here is an example.
(I will not share the identity of the paper)
Here is an example.
(I will not share the identity of the paper)
July 5, 2025 at 5:12 PM
After all these reports of authors adding language instructions for LLM reviews in their papers I wanted to check this myself and I downloaded the .tex source from one of these papers.
Here is an example.
(I will not share the identity of the paper)
Here is an example.
(I will not share the identity of the paper)
Reposted by Ahana D. (she/her)
WHAT ELSE DID THEY LIE ABOUT - dashare.zone ADMIN
June 15, 2025 at 6:07 PM
WHAT ELSE DID THEY LIE ABOUT - dashare.zone ADMIN
Reposted by Ahana D. (she/her)
Join us for Nneka's presentation tomorrow! Last talk before the summer break.
June 9, 2025 at 5:43 PM
Join us for Nneka's presentation tomorrow! Last talk before the summer break.
Reposted by Ahana D. (she/her)
new preprint with the amazing @lviano.bsky.social and @neu-rips.bsky.social on offline imitation learning! learned a lot :)
when the expert is hard to represent but the environment is simple, estimating a Q-value rather than the expert directly may be beneficial. lots of open questions left though!
when the expert is hard to represent but the environment is simple, estimating a Q-value rather than the expert directly may be beneficial. lots of open questions left though!
May 27, 2025 at 7:13 AM
new preprint with the amazing @lviano.bsky.social and @neu-rips.bsky.social on offline imitation learning! learned a lot :)
when the expert is hard to represent but the environment is simple, estimating a Q-value rather than the expert directly may be beneficial. lots of open questions left though!
when the expert is hard to represent but the environment is simple, estimating a Q-value rather than the expert directly may be beneficial. lots of open questions left though!
Reposted by Ahana D. (she/her)
new work on computing distances between stochastic processes ***based on sample paths only***! we can now:
- learn distances between Markov chains
- extract "encoder-decoder" pairs for representation learning
- with sample- and computational-complexity guarantees
read on for some quick details..
1/n
- learn distances between Markov chains
- extract "encoder-decoder" pairs for representation learning
- with sample- and computational-complexity guarantees
read on for some quick details..
1/n
May 26, 2025 at 1:27 PM
new work on computing distances between stochastic processes ***based on sample paths only***! we can now:
- learn distances between Markov chains
- extract "encoder-decoder" pairs for representation learning
- with sample- and computational-complexity guarantees
read on for some quick details..
1/n
- learn distances between Markov chains
- extract "encoder-decoder" pairs for representation learning
- with sample- and computational-complexity guarantees
read on for some quick details..
1/n
Reposted by Ahana D. (she/her)
"The chatbot responded that it was perfectly okay for landlords to discriminate based on whether those potential tenants need rental assistance"
From "Government officials are letting AI do their jobs. Badly," by @emilymbender.bsky.social & @alexhanna.bsky.social
thebulletin.org/2025/05/gove...
From "Government officials are letting AI do their jobs. Badly," by @emilymbender.bsky.social & @alexhanna.bsky.social
thebulletin.org/2025/05/gove...
Government officials are letting AI do their jobs. Badly
Offloading government responsibilities to AI can encourage discrimination, give wrong advice, and limit access to valid claims of asylum.
thebulletin.org
May 31, 2025 at 5:05 PM
"The chatbot responded that it was perfectly okay for landlords to discriminate based on whether those potential tenants need rental assistance"
From "Government officials are letting AI do their jobs. Badly," by @emilymbender.bsky.social & @alexhanna.bsky.social
thebulletin.org/2025/05/gove...
From "Government officials are letting AI do their jobs. Badly," by @emilymbender.bsky.social & @alexhanna.bsky.social
thebulletin.org/2025/05/gove...
Reposted by Ahana D. (she/her)
Disabled people have been pleading with folks to show solidarity for years.
We saw the rising tide of eugenics the moment everyone declared Covid over & decided to leave us by the wayside.
Pandemics give rise to fascism. What we’re seeing is the result of allowing disabled folks to be left behind
We saw the rising tide of eugenics the moment everyone declared Covid over & decided to leave us by the wayside.
Pandemics give rise to fascism. What we’re seeing is the result of allowing disabled folks to be left behind
May 21, 2025 at 5:01 AM
Disabled people have been pleading with folks to show solidarity for years.
We saw the rising tide of eugenics the moment everyone declared Covid over & decided to leave us by the wayside.
Pandemics give rise to fascism. What we’re seeing is the result of allowing disabled folks to be left behind
We saw the rising tide of eugenics the moment everyone declared Covid over & decided to leave us by the wayside.
Pandemics give rise to fascism. What we’re seeing is the result of allowing disabled folks to be left behind
Reposted by Ahana D. (she/her)
found a cool game theory book
arxiv.org/abs/1512.06808
arxiv.org/abs/1512.06808
May 21, 2025 at 10:18 AM
found a cool game theory book
arxiv.org/abs/1512.06808
arxiv.org/abs/1512.06808
Reposted by Ahana D. (she/her)
Trying to get my head round how this could make it to print. Many warning signs for all of us
This was just posted by @tbretc.bsky.social on another platform. The Chicago Sun-Times obviously gets ChatGPT to write a ‘summer reads’ feature almost entirely made up of real authors but completely fake books. What are we coming to?
May 20, 2025 at 11:26 AM
Trying to get my head round how this could make it to print. Many warning signs for all of us
Reposted by Ahana D. (she/her)
In the year of our Lord 2025... we are still putting on makeup on women without their consent.
It's truly like feminism never happened 🙅♀️
(I have been ranting about this ever since people started using it to demonstrate GANs back in the 2010s, I can't believe it's still an "acceptable" task in AI!)
It's truly like feminism never happened 🙅♀️
(I have been ranting about this ever since people started using it to demonstrate GANs back in the 2010s, I can't believe it's still an "acceptable" task in AI!)
May 8, 2025 at 3:24 PM
In the year of our Lord 2025... we are still putting on makeup on women without their consent.
It's truly like feminism never happened 🙅♀️
(I have been ranting about this ever since people started using it to demonstrate GANs back in the 2010s, I can't believe it's still an "acceptable" task in AI!)
It's truly like feminism never happened 🙅♀️
(I have been ranting about this ever since people started using it to demonstrate GANs back in the 2010s, I can't believe it's still an "acceptable" task in AI!)
I have started a substack lately on my random thoughts, if anyone's interested <3
Why I don't write in my mother tongue
an attempt to untangle my feelings about my mother tongue Bangla
open.substack.com
May 2, 2025 at 10:45 AM
I have started a substack lately on my random thoughts, if anyone's interested <3
Singapore book haul! (+ St Jordi)
April 28, 2025 at 1:44 PM
Singapore book haul! (+ St Jordi)
Had a lot of fun presenting our work at "Offline RL in Regular Decision Processes: Sample Efficiency via Language Metrics" at #ICLR2025, with my co-authors Alessandro Ronca and Sadegh Talebi!
check out our paper here: openreview.net/forum?id=EW6...
check out our paper here: openreview.net/forum?id=EW6...
April 27, 2025 at 6:32 PM
Had a lot of fun presenting our work at "Offline RL in Regular Decision Processes: Sample Efficiency via Language Metrics" at #ICLR2025, with my co-authors Alessandro Ronca and Sadegh Talebi!
check out our paper here: openreview.net/forum?id=EW6...
check out our paper here: openreview.net/forum?id=EW6...
Reposted by Ahana D. (she/her)
"It's wonderful watching the well of knowledge being poisoned in real time".
📷 Emily Gorcenski
📷 Emily Gorcenski
April 18, 2025 at 9:02 AM
"It's wonderful watching the well of knowledge being poisoned in real time".
📷 Emily Gorcenski
📷 Emily Gorcenski
Reposted by Ahana D. (she/her)
First draft online version of The RLHF Book is DONE. Recently I've been creating the advanced discussion chapters on everything from Constitutional AI to evaluation and character training, but I also sneak in consistent improvements to the RL specific chapter.
rlhfbook.com
rlhfbook.com
April 16, 2025 at 7:01 PM
First draft online version of The RLHF Book is DONE. Recently I've been creating the advanced discussion chapters on everything from Constitutional AI to evaluation and character training, but I also sneak in consistent improvements to the RL specific chapter.
rlhfbook.com
rlhfbook.com
A mid-week self reminder
April 16, 2025 at 10:25 AM
A mid-week self reminder
Reposted by Ahana D. (she/her)
A relatedly bad idea is working on research you don't deeply believe in for pragmatic reasons. You start with "oh, it'll be a quick low-hanging fruit project" and 9 months later you're still working on it and in despair
There's barely anything more soul-crushing than being bored. Structuring your entire life to avoid it? Great call.
April 16, 2025 at 3:22 AM
A relatedly bad idea is working on research you don't deeply believe in for pragmatic reasons. You start with "oh, it'll be a quick low-hanging fruit project" and 9 months later you're still working on it and in despair
Took a weekend off to travel to Bruges. It was beautiful :O
April 14, 2025 at 8:57 AM
Took a weekend off to travel to Bruges. It was beautiful :O
Reposted by Ahana D. (she/her)
Mark your calendars, EWRL is coming to Tübingen! 📅
When? September 17-19, 2025.
More news to come soon, stay tuned!
When? September 17-19, 2025.
More news to come soon, stay tuned!
April 8, 2025 at 8:33 AM
Mark your calendars, EWRL is coming to Tübingen! 📅
When? September 17-19, 2025.
More news to come soon, stay tuned!
When? September 17-19, 2025.
More news to come soon, stay tuned!
Reposted by Ahana D. (she/her)
Thought-canceling headphones
March 11, 2025 at 6:25 PM
Thought-canceling headphones
Reposted by Ahana D. (she/her)
Reposted by Ahana D. (she/her)
Congrats to this year's Turing award winners! www.nytimes.com/2025/03/05/t...
Incidentally, if you'd like to hear from them, we know a place they've given / are giving keynotes
Incidentally, if you'd like to hear from them, we know a place they've given / are giving keynotes
Turing Award Goes to A.I. Pioneers Andrew Barto and Richard Sutton
Andrew Barto and Richard Sutton developed reinforcement learning, a technique vital to chatbots like ChatGPT.
www.nytimes.com
March 7, 2025 at 2:38 AM
Congrats to this year's Turing award winners! www.nytimes.com/2025/03/05/t...
Incidentally, if you'd like to hear from them, we know a place they've given / are giving keynotes
Incidentally, if you'd like to hear from them, we know a place they've given / are giving keynotes
Made a small drawing in memory of my partner’s cat :’)
March 3, 2025 at 11:27 AM
Made a small drawing in memory of my partner’s cat :’)