@saiprasanna.in 🦋
@sai_prasanna
Followers
805
Following
20K
Media
453
Statuses
6K
🤖 = 42 Following the gradient of interestingness. RL² research (Reinforcement learning for Robot learning) https://t.co/UfG1FXfmGJ @ 🦋
GCU(eccentric) Gradient Ascent
Joined May 2009
Excited to share our research on improving zero-shot generalization (ZSG) of world models for Contextual RL. Joint work with @karim_farid0, @RaghuSpaceRajan, and @AndreBiedenkapp to be presented at the RLC 2024 (@RL_Conference).
2
6
46
RT @creus_roger: 🚨 Excited to share our new work: "Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning"! 📈. We pro….
0
33
0
RT @pcastr: really excited about this new work we just put out, led by my students @creus_roger & @johanobandoc , where we examine the chal….
0
10
0
RT @VeronicaChelu: Excited to share that I’ll be starting as a postdoc in Rose Bagot's lab at @mcgillu , studying the neural mechanisms of….
0
1
0
RT @FrankRHutter: The data science revolution is getting closer. TabPFN v2 is published in Nature: On tabular class….
0
253
0
0
4
0
RT @UCL_DARK: DARK lab is now also on That Other Place 🦋. Our members are already actively discussing AI on the butterfly. Come be one of o….
0
2
0
Putting this work in perspective and potential future works: Only on bsky
0
0
0
My bsky feed now has more signal than here. Looks more and mote like it's so over here with probability> 90% let's see.
0
0
0
Lol my ML/AI feed here is growing more silent and has more or less shifted to bsky completely. Join us there 🦋.
0
0
0
RT @ClementBonnet16: Introducing Latent Program Network (LPN), a new architecture for inductive program synthesis that builds in test-time….
0
31
0
RT @apsarathchandar: At @ChandarLab, we are happy to announce the second edition of our assistance program to provide feedback for members….
0
36
0
RT @vwxyzjn: @creus_roger just implemented a @cleanrl_lib Parallel Q-Networks algorithm (PQN) implementation! . 🚀PQN is DQN without a repla….
0
12
0
RT @TomNotGeorge: SIMPL outperforms CEBRA — a contemporary, more general-purpose, neural-net-based technique — in terms of performance and….
0
1
0
RT @mitrma: We are very excited to announce Kinetix: an open-ended universe of physics-based tasks for RL!. We use Kinetix to train a gener….
0
216
0
Bluesky is hitting a big threshold of ml people migrating from this garbage pile! Join us there!! So many stater packs to fill your feed without puppet master throwing political garbage at you.
0
0
1
RT @nsaphra: If you’re considering moving on from this garbage feed, AI bksy is hitting its hockey stick era.
0
6
0
What weird audio latent spaces are you currently inhabiting? Me .
open.spotify.com
Various Artists · Compilation · 2017 · 10 songs
0
0
0
RT @TankredSaanum: Object slots are great for compositional generalization, but can models without these inductive biases learn composition….
0
15
0
If anyone among you is at EWRL, Toulouse, let's meet up!.
0
0
1