torchrl @torchrl1
TorchRL is the open-source Reinforcement Learning (RL) library for PyTorch. github.com/pytorch/rl Joined August 2022-
Tweets143
-
Followers648
-
Following172
-
Likes365
FAIR researchers (@AIatMeta) presented SegmentAnything and our robotics work at the White House correspondents’ weekend. Llama3 + Sim2Real skills (trained with @ai_habitat) = a robot assistant
FAIR researchers (@AIatMeta) presented SegmentAnything and our robotics work at the White House correspondents’ weekend. Llama3 + Sim2Real skills (trained with @ai_habitat) = a robot assistant https://t.co/YNmHyVxvtO
Come and meet us at #ICLR2024 next week. TorchRL paper was accepted as a spotlight poster, come and admire it on Thursday morning. We will also have 2 daily sessions (10 and 3pm) demoing the library at the Meta booth!
🔥 #MyoSuite 2.3.0 is out! You can now use it with any #Gym & #Gymnasium library! Seamless integration with hashtag#TorchRL 🙌 As always, just `pip install myosuite` sites.google.com/view/myosuite
We're on fire TorchRL 0.4 just landed too! More flexibility with replay buffers, better video recording tools, and loads of improvements with the environment API! Check the release note: github.com/pytorch/rl/rel… and install the package now `pip install torchrl`
Just opened a tensordict discord! discord.gg/tz3TgTAe3D Join us there to talk about features, ask questions and make TD even better
Thanks @TalkRLPodcast for hosting us!
Thanks @TalkRLPodcast for hosting us!
The new version of robohive uses the same dispatching mechanism as torchrl to support m̵u̵l̵t̵i̵p̵l̵e̵ all versions of gym so you don't need to care about which one you want to rely on. As always, the new version is 100% compatible with torchrl! Check it out
The new version of robohive uses the same dispatching mechanism as torchrl to support m̵u̵l̵t̵i̵p̵l̵e̵ all versions of gym so you don't need to care about which one you want to rely on. As always, the new version is 100% compatible with torchrl! Check it out
🚨 New paper 🚨 on teaching LLMs to reason with RL! 🔎 We find that expert iteration (aka iterative rejection sampling) is a strong baseline, matching PPO's asymptotic performance and sample efficiency. 🙌 Kudos to @Dahoas1 who is a super productive researcher and produced not…
🚨 New paper 🚨 on teaching LLMs to reason with RL! 🔎 We find that expert iteration (aka iterative rejection sampling) is a strong baseline, matching PPO's asymptotic performance and sample efficiency. 🙌 Kudos to @Dahoas1 who is a super productive researcher and produced not…
@francoisfleuret functorch.dim and its docs. used to be here but it's upstreamed now to functorch.dim github.com/facebookresear…
Career update: I am co-founding a new research group called "GEAR" at NVIDIA, with my long-time friend and collaborator Prof. @yukez. GEAR stands for Generalist Embodied Agent Research. We believe in a future where every machine that moves will be autonomous, and robots and…
The RLC submission page is now open! Get your submissions ready: openreview.net/group?id=rl-co…
Dive also into the latest Tensordict release — it's an absolute blast!
Dive also into the latest Tensordict release — it's an absolute blast!
Vihang Patil @wehungpatil
146 Followers 244 Following PhD student under @HochreiterSepp, working on Reinforcement Learning at the Institute for Machine Learning, Linz. Also, Intern @AmazonScienceTianyue Wu @Modern_Gangster
45 Followers 202 Following Loving self-closed-loop robotics, from model-based optimization to visuomotor skills. Looking forward physical agi...Welt Meister (AI Clim.. @Welt__Meister__
672 Followers 4K Following Retvrn to Pangea Globohomo SupporterMindi Broks @broks_min
45 Followers 5K FollowingHarriet Felty @FeltyHarri56604
79 Followers 5K FollowingSimon LC @simonlc_
484 Followers 208 Following research scientist @ the AI institute robotics & optimization phd @ stanfordMohammad R. Samsami @.. @M_R_Samsami
279 Followers 361 Following AI Researcher at @Mila_Quebec & @ServiceNowRSRCH. Developing agents capable of reasoning in complex situations. Ex-intern at @EPFL_en.Ashley Merlain @AshleyMerl69901
74 Followers 5K FollowingMowbray @MowbrayRv
31 Followers 989 Following Graduate student @iitmadras Area : Reinforcement learning, controls & optimizationDipam Patel @_dipam_
7 Followers 626 FollowingVismay Vora @voravismay9
124 Followers 2K Following A curious and hungry geek focused on excelling everyday. Enjoy learning and always on the lookout for insights.Daniel @danilyn_4
32 Followers 1K FollowingSr. Bot @joseluHAL
118 Followers 671 Following Research in RL, dancing techno to the dawn, you can always find me checking some tasty food :Dwhyoverfitting @whyoverfitting
83 Followers 456 Following Machine Learning Engineer at a Big Tech Company. Physicist. Mathematician. Recent Kaggler. All opinions are my own. (e/SARIMAX).Gene @_francis_lewis
84 Followers 238 Following its working | droids @anduriltech | prev @stanfordsvlHao Zhu 朱昊 @_Hao_Zhu
1K Followers 831 Following PhD student @LTIatCMU. Building real world cooperative AI. intersection of Language/Social Intelligence/Embodiment/Robotics/Cognitive Science. he/him/他.Horace He @cHHillee
24K Followers 449 Following Working at the intersection of ML and Systems @ PyTorch "My learning style is Horace twitter threads" - @typedfemaleIgor Garbuz @igarbuz
102 Followers 311 Following Modeling the world with SGD, one batch at a time. Alumni @42born2code. Freelance in ML.Jeff Xu @jjx003
54 Followers 1K FollowingHuy Tran @huytransformer
104 Followers 3K Followingel Axioma De ?•¿{:.. @edealba_
679 Followers 1K Following aspiring surrealist 👻 &expressivist that digs std::mathematical / neo-pythagorean realism and 𝐒𝐄𝐋𝐅-𝐑𝐄𝐅𝐄𝐑𝐄𝐍𝐓𝐈𝐀𝐋𝐈𝐒𝐌: https://t.co/InBKdqbXpF {ø,};°Syble Mellage @MellageSyb82849
87 Followers 5K FollowingAlexandre Manai @_IOkkOl
8 Followers 129 Following 🤖 Exploring the frontiers of Machine Learning & Reinforcement Learning. Here to connect, share insights, and learn. Let's talk AI! #MachineLearning #AIAya Shabbar @shabbaraya
1 Followers 49 Following CS Research; Reinforcement Learning, DeepRL, Statistical RL, and Machine Learning with New-Media Art in between.Kinley Lawman @lawm_kinl
17 Followers 3K FollowingManan Suri @MananSuri27
0 Followers 36 FollowingPura Whiter @pura_whit
30 Followers 5K FollowingCiro Cavani @CiroCavani
111 Followers 334 FollowingKhadijah Boch @boch_khadi
40 Followers 5K Following1mk0goq2yin4 @q7bfwdorcnag
9 Followers 518 FollowingZenobia Mcglocklin @ZenobiaMcg36921
37 Followers 5K FollowingGert-Jan @GJ_Both
225 Followers 542 Following Machine Learning Researcher @ TuragaLab, Janelia | Computational Optic, ML and Connectomics | Physics & ML1 @jwqc2sdwdm
26 Followers 73 FollowingTera Nguy @NguyTera42648
75 Followers 5K FollowingCrystal Mickels @CrystalMic58397
66 Followers 5K FollowingDavid (Braginsky) Blo.. @daveey
151 Followers 289 Following AI researcher - multi-agent RL in complex social environments. @pluralityInst co-founder - human collaboration at scaleAitana Zacchini @AitanaZacchin
55 Followers 5K FollowingHope Dichristopher @HopeD1474
69 Followers 5K FollowingWillie Given @GivenWilli87720
33 Followers 5K FollowingAmine ANDAM ⴰⵎⵉ.. @AmineAndam
189 Followers 3K Following PhD student @UM6PCC | #RL for #Cybersecurity of #Metaversevibhor @vib_hor
38 Followers 596 FollowingRiskMeterSci007 @RiskMeterSci007
281 Followers 1K FollowingJuan Gómez Romero @j_gomero
195 Followers 278 Following CU en @CanalUGR. Inteligencia Artificial y otros animales / Professor at Universidad de Granada. Artificial Intelligence and other animals.Mehrdad Moghimi @MehrdadM96
6 Followers 153 Following PhD Student at @YorkUniversity, Interested in risk-sensitive #ReinforcementLearningAndreas Kirsch 🇮�.. @BlackHC
9K Followers 5K Following Past: 🧑🎓 DPhil @AIMS_oxford @ExeterCollegeOx @UniofOxford (4.5yr) 🧙♂️ RE @DeepMind (1yr) 📺 SWE @Google (3yrs) 🎓 @TU_Muenchen 👤 Fellow @nwspkChris Paxton @chris_j_paxton
8K Followers 2K Following Mostly posting about robots. Embodied AI @hellorobotinc, formerly @AIatMeta, @NVIDIAAI, @zoox. All views my own.Stone Tao @Stone_Tao
2K Followers 870 Following PhD @UCSanDiego @HaoSuLabUCSD working on scalable robot learning and embodied AI. Co-founded @LuxAIChallenge to build AI competitions. @NSF GRFP fellowJoseph Suarez (e/🐡.. @jsuarez5341
2K Followers 63 Following MIT PhD candidate, creator of Neural MMO (https://t.co/NaaDv6UQlN), PufferLib (https://t.co/43D0orh0lJ). Open-source RLSimon Prince @SimonPrinceAI
9K Followers 333 Following Professor of Computer Science, University of BathSharath Raparthy @sharathraparthy
1K Followers 590 Following AI Research at @MetaAI | Building llamas 🦙AGI.Eth @ceobillionaire
155K Followers 4K Following Vincent Boucher, President of @Montreal_AI #MontrealAI | B. Sc. Physics, M. A. Govt. Policy Analysis and M. Sc. Aerospace Engineering | $AGI by AGI.Eth #AGIVincent François-Lav.. @VinFL
2K Followers 766 Following Assistant Professor in machine learning @VUAmsterdam. Abstract representations+Learning+Reasoning. Deep RL book: https://t.co/09Gk8lkE7o.Noam Brown @polynoamial
34K Followers 612 Following Researching reasoning @OpenAI | Co-created Libratus/Pluribus, the first superhuman no-limit poker AIs | Co-created CICERO | PhD from @SCSatCMUDavi Sidarta-Oliveira.. @davisidarta
1K Followers 574 Following 1st Gen. Single-cell bioinformatics. Neuroimmunometabolism. AI dreams for fun. Postdoc @UniofOxford at the @AnaDomingosLabRL_Conference @RL_Conference
2K Followers 240 Following Home of the first annual reinforcement learning conference. Stay tuned up for updates!Ross Taylor @rosstaylor90
6K Followers 881 Following Something new 🥷. Previously: @paperswithcode, reasoning lead @metaai, Galactica LLM lead, Atlas ML (acq by Meta)Homanga Bharadhwaj @mangahomanga
1K Followers 523 Following PhD student @SCSatCMU. Visiting researcher @MetaAI. Hater of hot takes. Lover of analyses.Pierluca D'Oro @proceduralia
1K Followers 359 Following Final-year PhD student at Mila and researcher at Meta, working on the science of AI agents. Made in Sicily.Guillaume Durandau @GDurandau
371 Followers 298 Following 🇫🇷 Assistant professor @ McGill 🇨🇦 |NeuRoc Lab| Neuromechanics and wearable roboticsSaran Tunyasuvunakool @saran__t
295 Followers 67 Following Senior Staff Research Engineer @GoogleDeepMind, Tech Lead for the #MuJoCo Physics Simulator ⚙️ Numericist, Black Hole Physicist, and Mathematician by training.Yunlong Song @realyunlong
298 Followers 409 Following Visiting researcher at MIT. Ph.D. student at Robotics and Perception Group. Opinions are my own.Sam Gross @colesbury
2K Followers 110 FollowingBolland Adrien @AdrienBolland
218 Followers 721 Following Researcher in Deep RL with applications to the Renewable Energy Transition - Opinions are my own until I change my mind.Antonin Raffin @araffin2
3K Followers 373 Following Researcher in robotics and machine learning (Reinforcement Learning). Maintainer of Stable-Baselines. Links to find me on other platforms are on my homepage 🐘Neuromechanics Lab is.. @NeuromechanicsL
3K Followers 1K Following Lena Ting's Neuromechanics Lab at Emory University. We got balance. @BME_GT_EmoryAlberto Chiappa @chiappa_alberto
81 Followers 71 Following PhD Student in Computational Neuroscience and AI @EPFLMyoSuite @MyoSuite
583 Followers 34 Following In pursuit of human level dexterity & agility in physiological human digital twinsVittorio Caggiano @CaggianoVitt
331 Followers 290 Following TPM & Research @ MetaAI l ex-IBM ResearchGilles Louppe @glouppe
9K Followers 2K Following On a quest to accelerate Science with #AI. Professor of AI and deep learning @UniversiteLiege. Previously @CERN, @nyuniversity.Matteo Bettini @MatteoBettini98
16 Followers 16 FollowingMatt Botvinick @mattbotvinick
819 Followers 31 Following Senior Technology and Policy Advisor @DeepMindPierre Schumacher @rlfromlux
966 Followers 826 Following PhD Student @MPI_IS reinforcement learning for biomechanics | robotics | natural motion. MyoChallenge Organizer. @CMU_robotics visiting scholarNatasha Jaques @natashajaques
25K Followers 1K Following Senior Research Scientist at @GoogleAI and Assistant Professor @uwcse. Social Reinforcement Learning in multi-agent and human-AI interactions. PhD from @MIT.Shashank Prasanna @shshnkp
1K Followers 169 Following I talk/write/teach/build AI/ML. Recreational runner🏃♂️. Passionate about Math. Physics. HPC. GPU. AI accelerators. @modular. My own opinions ↓TalkRL Podcast @TalkRLPodcast
3K Followers 58 Following TalkRL Podcast is All Reinforcement Learning, All the Time. Follow for interviews with brilliant folks from across the world of RL. Host @robinc. DMs open.Kornia @kornia_foss
5K Followers 2K Following Advancing Computer Vision & Spatial AI, openly #computervision #opensource #AIAnton Bakhtin @ SF @anton_bakhtin
2K Followers 126 Following MTS at @AnthropicAI, Ex @MetaAI, Ex @Google Three logicians walk into a bar ...Matteo Papini @papinimat
439 Followers 721 Following Assistant professor @polimi. Reinforcement Learning. Previously postdoctoral researcher at @UPFBarcelona. Co-organizer of @RLSummerSchool 2023.Aravind Rajeswaran @aravindr93
3K Followers 168 Following Research Scientist at FAIR (@MetaAI) Formerly at @OpenAI and @GoogleAI PhD from @uwcse and BTech from @iitmadrasJason Ma @JasonMa2020
1K Followers 993 Following PhD @Penn and @GoogleDeepMind. Apple Scholars in AI/ML. Prev: @NVIDIAAI, @MetaAI, @Harvard. Foundation Models for RoboticsVikash Kumar ✈️IC.. @Vikashplus
4K Followers 408 Following Studying intelligent embodied behaviors. Ad. Prof. @CMU_Robotic | Sr. research scientist at @AIatMeta @GoogleAI @OpenAI | @berkeley_ai @UWcse #MuJoCoKevin Mets @kemets
411 Followers 2K Following Tenure Track Assistant Professor @IDLabResearch @UAntwerpen @imec_int . Reinforcement learning. Graph neural networks. Board game geek.Yisong Yue @yisongyue
19K Followers 3K Following Machine Learning @Caltech (@YueLabCaltech). AI for invention at @AsariAILabs. Autonomous Driving at https://t.co/riZHAmvcAr. Senior Program Chair @iclr_conf.Xavier Puig @xavierpuigf
1K Followers 820 Following Research Scientist at FAIR @AIatMeta working on EmbodiedAI | PhD @MIT_CSAILFabio Pardo @PardoFab
1K Followers 442 Following Research Scientist at @GoogleDeepMind Toronto. Previously at @ImperialCollege, @Sorbonne_Univ_ and @ENS_ULM. Author of the Tonic RL library.Politecnico di Milano @polimi
44K Followers 294 Following Il Politecnico di Milano è un'università scientifico-tecnologica che forma ingegneri, architetti e designer.Meta Open Source @MetaOpenSource
158K Followers 568 Following Empowering diverse community through open source technology.Julian Schrittwieser @Mononofu
4K Followers 68 Following Principal Research Engineer at DeepMind Gemini RL AlphaGo, AlphaZero, MuZero, AlphaCode, AlphaTensor 日本語を勉強しているTaylor W. Killian @tw_killian
2K Followers 767 Following #ML4H research @UofT/@VectorInst interested in Decision Making & Transfer Learning, visiting @MIT // @BYU '13; @Harvard '17Fabio Petroni @Fabio_Petroni
2K Followers 348 Following Co-Founder & CTO @Samaya_AI, focusing on machine knowledge. Former Researcher, Engineer and Manager @MetaAI (FAIR) @thomsonreuters @KPMG, PhD @SapienzaRoma.Aslan Bakirov @abekir
455 Followers 5K Following Causal Machine Learning @causalens. Loves AI4Science. Formerly: @Meta @unibogazici_enPascal Leroy @PaLeroy
157 Followers 453 Following PhD Student @UniversiteLiege - Interested in Multi-agent RLWho doesn’t love good methods for reward inference. What if I told you that you could extract dense rewards from video, by ranking frames temporally using the BT model from RLHF (aka just doing temporal classification with cross-entropy). Let's see how, in rank2reward - a🧵(1/10)
FAIR researchers (@AIatMeta) presented SegmentAnything and our robotics work at the White House correspondents’ weekend. Llama3 + Sim2Real skills (trained with @ai_habitat) = a robot assistant
Washingtonians delved into the world of artificial intelligence (AI) at the Washington AI Network’s inaugural weekend TGAIFriday Lunch for White House correspondents. trib.al/FwHF9Um
Looks like Billy Joel was right: Vienna waits for me! Funnily enough, he even got the time signature right -- 4/4 :p. Jokes aside, two #icml2024 papers I can share already (SPO: arxiv.org/abs/2401.04056, Hybrid IRL: arxiv.org/abs/2402.08848), two more coming soon!
🔥 #MyoSuite 2.3.0 is out! You can now use it with any #Gym & #Gymnasium library! Seamless integration with hashtag#TorchRL 🙌 As always, just `pip install myosuite` sites.google.com/view/myosuite
📢 Open PhD position in my group, on simulation-based inference and generative models for particle physics, on a joint project with Fabio Maltoni and Tilman Plehn inspirehep.net/jobs/2769416
The position is still open! 👇
📢 Open PhD position in my group, on simulation-based inference and generative models for particle physics, on a joint project with Fabio Maltoni and Tilman Plehn inspirehep.net/jobs/2769416
#TorchRL 0.4 is out, with increased flexibility around replay buffers & visual inputs! 💪 The team has been iterating fast🔥🚀. Take it for a sping and send us feedback!
We're on fire TorchRL 0.4 just landed too! More flexibility with replay buffers, better video recording tools, and loads of improvements with the environment API! Check the release note: github.com/pytorch/rl/rel… and install the package now `pip install torchrl`
Excited to unveil Orbit v0.3 with many new features & improvements. Orbit is a modular robot learning framework that leverages the latest simulation capabilities and supports different learning paradigms! Join us in revolutionizing robotics! More info here isaac-orbit.github.io/orbit/
@leggedrobotics Excellent work! Given its relevance, please consider joining us at @ieee_ras_icra workshop. Invitations are open for posters/ demos/ panels. Looking forward to meeting you at ICRA. x.com/myosuite/statu…
Join us at @ieee_ras_icra for our workshop on Expanding the Frontiers of Sim2Real. Book the full day of 17 of June @ PACIFICO Yokohama 🇯🇵. We have an exciting lineup of speakers going from Robotic, Plasma to Biomechanics. We are also welcoming posters. 🔗tinyurl.com/icra24Sim2Real
@sagecodes Maybe just the torchrl docs, Sutton & Barto’s book, OpenAI’s Spinning up in Deep RL, UCL’s lecture series on YouTube, Artificial intelligence a modern approach also has a chapter on RL
@karpathy @danielsateler1 I think some day, projects like PyTorch will make users pay only for the overhead they use. Lots of R&D needed to get there: compiler technology, type systems, various other things. Actually, LuaJIT was really cool in that aspect -- one of the most brilliant pieces of…
Kudos to @VincentMoens for enabling pointwise arithmetic operations (using foreach) in tensordicts (data structure for @torchrl1 )! github.com/pytorch/tensor… This should be helpful for usecases like implementing optimizers!
Great opportunity to work on an interesting problem and learn from an amazing team!
Our group at FAIR is hiring postdoctoral researchers to develop the future of human/machine communication! Please apply directly at metacareers.com/jobs/380024285… or reach out in DM/email
🚨We're building something unique toward @vkhosla's #1 👀 We're #hiring for a role in language-based reasoning between human embodiments <intern🌐/FTE(preferably🇺🇸)> 💪Got a knack for complex multi-modal reasoning? Got an exceptional understanding of #LLM APIs? 📩Drop me a DM
reach out to @Vikashplus if you are interested in complex multi-modal reasoning and want to make something truly outstanding!
Some personal news: I’m excited to be joining Hello Robot, to lead their Embodied AI effort! For years now, I’ve been a passionate supporter of their vision of affordable, useful robots that can help people out with their day-to-day lives. I’ve previously worked at FAIR, part of…
@amritwt The video is actually from 1989, but who is counting!