Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @rl_agent
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @rl_agent
-
Video & slides for LIRE workshop @
#NeurIPS2019 are now up: https://sites.google.com/view/neurips2019lire/schedule … Check out the Talks and Panel by@RaiaHadsell@tommmitchell Jeff Bilmes@pabbeel@YejinChoinka Tom Griffiths & more. Thanks to all speakers & presenters for making the workshop a success!pic.twitter.com/2WvsHpEkyZ
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
Congratulations to the MLD TA Awards 2019 recipients Liam Li, Lisa Lee, Nicholay Topin, Paul Liang, and Maruan Al-Shedivat! Being a TA in
#ML is challenging and significant. We are incredibly thankful for all of your efforts -https://mld.ai/ta2019Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
Nice work from Lisa, Ben, Sergey et al! State marginal matching offers a new paradigm for teaching skills, differing from stationary reward maximization or imitation from demos. Inspired parts of our recent work! https://arxiv.org/abs/1906.05274
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
(first tweet!) Our paper got Best Paper Award at CoRL 2019! A summary and extension of imitation learning methods and their application to state marginal matching.https://drive.google.com/file/d/1VUSqo4Vs-qi94pzWGzuEMguR_P-3jZQF/view …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I just started at Stanford this week as a visiting researcher in
@chelseabfinn's lab, and I'm also still part-time at Google Brain Robotics. If you're around in the area and would like to chat about research, please feel free to reach out anytime! (My office is in Gates)Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
We're organizing
#NeurIPS2019 workshop on Learning with Rich Experience: Integration of Learning Paradigms, w/ an amazing lineup of speakers! Deadline: Sept 11 w/@andrewgwils@chelseabfinn@rl_agent@Lianhuiq Taylor Berg-Kirkpatrick@rsalakhu & Eric Xinghttps://sites.google.com/view/neurips2019lire …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
Code by
@rl_agent for State Marginal Matching: Learning an exploration policy for which the state marginal distribution matches a given target distribution, incorporating prior knowledge about task https://sites.google.com/view/state-marginal-matching … Paper:https://arxiv.org/abs/1906.05274 Code:https://github.com/RLAgent/state-marginal-matching …https://twitter.com/rl_agent/status/1141054794246737920 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We've released our code for State Marginal Matching: a principled objective that explores well in multi-task settings, easily incorporates prior knowledge, & unifies previous exploration methods. http://sites.google.com/view/state-marginal-matching … w/ B Eysenbach, E Parisotto, E Xing
@svlevine@rsalakhupic.twitter.com/2WyvUzAmYCHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Congratulations & thanks Kamalika (
@kamalikac) and Russ (@rsalakhu) for organizing#ICML2019! And thanks for having us workflow chairs onboard! It was an amazing experience to see the conference come together from start to finish.@dchaplot@pliang279https://twitter.com/rsalakhu/status/1139968167587921920 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
Can we learn policies that match *state distributions* (randomly visit states with a desired distr.)? This generalization of RL is useful for exploration. Exploration via State Marginal Matching, w/
@rl_agent, B. Eysenbach, E. Parisotto, E. Xing,@rsalakhu https://arxiv.org/abs/1906.05274 pic.twitter.com/AlgMeud4r5
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
Can we use reinforcement learning together with search to solve temporally extended tasks? In Search on the Replay Buffer (w/ Ben Eysenbach and
@rsalakhu), we use goal-conditioned policies to build a graph for search. Paper: https://arxiv.org/abs/1906.05253 Colab:http://bit.ly/rl_searchHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
For the first time in a major machine learning conference
#icml2019@kamalikac and I implemented a new Code-at-Submit-Time measure and we are delighted by the strong community response. Read about the outcome here:https://medium.com/@kamalika_19878/the-icml-2019-code-at-submit-time-experiment-f73872c23c55 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
Check out Lisa Lee's
@rl_agent and Ben Eysenbach's Contributed Talks @#iclr2019 Monday workshops on Exploration & Meta-RL via State Marginal Matching: https://leelisa.com/pdf/state_marginal_matching.pdf …https://twitter.com/rl_agent/status/1125095512393252866 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Excited to give two Contributed Talks @
#iclr2019 on Monday w/ Ben Eysenbach on our new work: Exploration & Meta-RL via State Marginal Matching https://leelisa.com/pdf/state_marginal_matching.pdf … w/ Ben, Emilio@rsalakhu@svlevine 12:15 @ TARL https://tarl2019.github.io/#schedule 15:50 @ SPiRL http://spirl.info/2019/program pic.twitter.com/h26IYmrJ3wHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I wrote a Colab tutorial on MaxEnt RL: https://colab.research.google.com/drive/1VkoRfg_thJuRyWlZXFNvPcRrviRlxO9I … It implements the graphical model from
@svlevine's "RL as Inference" tutorial for a simple chain environment. Play around with the reward function to learn different policies using the forward-backward algorithm!Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Lisa Lee proslijedio/la je Tweet
And also big thanks to our ICML workflow chairs
@rl_agent,@pliang279 and@dchaplot for their huge help!https://twitter.com/kamalikac/status/1120121694188785664 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Check out Emilio's new paper: Concurrent Meta Reinforcement Learning https://arxiv.org/abs/1903.02710 (w/
@Yuhu_ai_,@rsalakhu, and others) tl;dr CMRL learns a multi-agent communication protocol to coordinate exploration between parallel rollout agents.Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
Posted a new paper on Embodied Multimodal Multitask Learning for semantic goal navigation and embodied question answering. (with
@rl_agent,@rsalakhu,@deviparikh,@DhruvBatraDB) PDF: https://arxiv.org/pdf/1902.01385.pdf … Demo Videos: https://devendrachaplot.github.io/projects/EMML pic.twitter.com/ilVGQR9mMXPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lisa Lee proslijedio/la je Tweet
Work led by Devendra Chaplot (
@dchaplot) and Lisa Lee (@rl_agent)!https://twitter.com/arXiv_Daily/status/1092817481440256000 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.