Elad Hazan: Returning from a fantastic workshop ...| Robocrunch AI

Returning from a fantastic workshop at Simons/Berkeley on MARL. My talk about multi-agent control/RL now available at: https://t.co/X6WYrzGdSC
— Elad Hazan (@HazanPrinceton) May 7, 2022

Exploring the social aspects of intelligent agents, here we develop a Multi-Agent RL (MARL) algorithm to socially coordinate the individual behaviors, with collective behaviors emerging. Work to be presented at NeurIPS'21 Project page: https://t.co/RnAGDZrOFX

Shared by Bolei Zhou at 10/28/2021

Today @iclr_conf learn more about a mechanism by which non-stationary prediction targets can prevent learning progress in deep RL agents. By Clare Lyle, Mark Rowland, and @wwdabney. See the schedule for more: https://t.co/AWDVuHoOee #ICLR2022

Shared by DeepMind at 4/27/2022

Great to see this new work on Vygotskian RL agents @jayelmnop @ai_ucl ! (= language used as a cognitive tool for exploration, planning, imagination in Deep RL). The community working on this key topic is growing: https://t.co/Kp9FMPUE3a @cedcolas @karch_tristan @Clement_MF_

Shared by Pierre-Yves Oudeyer at 4/4/2022

Today (5/5) 4pm EDT, Ruslan Salakhutdinov @rsalakhu from CMU @SCSatCMU @mldcmu will be giving a talk at the Embodied Intelligence Seminar @MIT_CSAIL on building autonomous embodied agents! Live-streaming from: https://t.co/bQToLGI0qY…, co-hosted with @EpisodeYang!

Shared by Yilun Du at 5/5/2022

Need your #nlproc fix after your #ACL2022 notifications? Join @wing_nus for @YiTayML's "transformers for IR" & @lmthang's "self-training V+L" lectures on 1 Mar 11am-1pm SGT (UTC+8; UTC 3-5am). DM @knmnyn for live talk 🔗. Slides & vid to be post-released. Re: for the abstracts

Shared by Min-Yen Kan at 2/25/2022

Today @iclr_conf, see how an RL agent can use demonstration based goal conditioning to effectively learn to perform complex long-horizon manipulation tasks. https://t.co/THZB7peG8v #ICLR2022

Shared by DeepMind at 4/28/2022

768