Medijski sadržaj
- Tweetovi
- Tweetovi i odgovori
- Medijski sadržaj, trenutna stranica.
-
2017:Successor Features for Transfer in RL 2019:Universal Successor Features for Transfer Reinforcement Learning 2020:Fast Task Inference with Variational Intrinsic Successor Features Robotics: Visual Semantic Planning using Deep Successor Representationshttps://www.youtube.com/watch?v=_2pYVw6ATKo …
-
Hi friends. Inspired by Tolman, who was vocally political, here’s a political tweet against a war with Iran. We held a peaceful protest near prospect park in Brooklyn where senator
@SenSchumer lives. We hope he reflects the anti war voices of NY. Next: Tomorrow 11am time square.pic.twitter.com/ZYQ7dctzjw
-
Representing cog comp neuro here. Note that there's also critiques/revisions to the three levels in cognitive science. A notable critique comes from Danks, arguing that cognitive theory is not adequately captured by Marr's levels, arguing for "constraint" rather than reduction.pic.twitter.com/II9tl2B7qk
-
The videos of our talks at the
#NeurIPS2019 workshop on "Biological and Artificial Reinforcement Learning" are online. Many thanks to@FeryalMP@RaymondRChua@sarazann2 :) If you were so inclined, you can find my talk at 1:02:15 in this link: https://slideslive.com/38921887/biological-and-artificial-reinforcement-learning-2 …pic.twitter.com/i6PCXq8xlm
-
Superdyna is here! An integrated approach to AI agents who can find their way around the world by discovery and aberration. :)pic.twitter.com/FwQ0Hk3fTR
Prikaži ovu nit -
Inspired by play, we need a set of good subproblems. They come from state features. State feature attainment is a distinct subproblem. 5/npic.twitter.com/8TN8g0nMpI
Prikaži ovu nit -
Expectation planning better than other approaches to looksheads and updateds. 4/npic.twitter.com/gMbakfVKcB
Prikaži ovu nit -
This is a follow up to the 1990 Dyna that works like this: 3/npic.twitter.com/26VsmplRen
Prikaži ovu nit -
The world is complex and super dyna needs to handle partial observations and online TD learning to extract options and build a world model. 2/npic.twitter.com/pYV7tGlyaN
Prikaži ovu nit -
Will tweet about Rich Sutton’s talk on SuperDyna :) @
#NeurIPS2019pic.twitter.com/mQFZu8MbSR
Prikaži ovu nit -
Excellent talk by Eszter Vertez (with Maneesh Sahani) on a neurally plausible model learning successor representation in partially observable environments.
#NeurIPS2019pic.twitter.com/yix76FhkmM
-
Not the robot we wanted, but the robot we deserved.
@ #NeurIPS2019pic.twitter.com/9euL3lZLTc
-
Finally met
@profcikara in person
Need more of this=> champagne
food & lots of dessert
with past & future coauthors Mina, @iamlindachang@beausievers! So much fun! It fueled my 7 total hours of talk & python workshop over 2 days &
brainstorms! Can’t wait for next phase!pic.twitter.com/qWiiG4D2hs
-
Same! For me it’s like a split personality: OCD about typos when proofreading someone else’s work and dyslexic when it comes to proofreading my own!pic.twitter.com/Ippr2aES4E
-
After extensive experience with university admin in four different countries, I am profoundly grateful for the special level of patience, kindness, & support I have received from admins in US universities both at Princeton & Columbia. Without them I would have drowned in paper!
pic.twitter.com/m0q9sm3guW -
Lol confounded design -> over-the-wall & under-the-stairs goal vectorspic.twitter.com/yFPAmmxT1z
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.
