Pablo Tano
@pablo_tano8
Followers
86
Following
257
Media
11
Statuses
39
RT @paul_masset: Our work with @pablo_tano8 ,.@HyungGoo_Kim @AtharNMalik @pouget_alex .and Nao Uchida exploring how dopamine neurons could….
nature.com
Nature - Individual dopaminergic neurons encode future rewards over distinct temporal horizons.
0
30
0
RT @BakermansJJW: Happy to share the latest version of our work on compositional cognitive maps in hippocampus, with Jo Warren, @jrcwhittin….
0
36
0
Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.
661
2K
9K
0
0
2
We called the curriculum Static to Dynamic Stabilization—a method that not only won the @Meta motor control competition but also enabled us to compare dimensionality and synergies between biological and artificial motor control.
1
0
1
We trained a musculoskeletal hand to master a complex manipulation task—a first of its kind. After weeks of testing (and failing) with every RL algorithm, I discovered a simple yet powerful approach: start with stable configurations, then gradually merge them at higher speeds.
1
0
2
Thrilled to see our work featured on the cover of Neuron!.
Here's our latest issue: The cover is for @TrackingPlumes & coll.'s work on a novel learning algorithm for skilled motor control learning, that you can read in full here or in a Preview by @ScottLIMBlab
1
0
5
RT @TrackingPlumes: How does the brain control the numerous muscles of the body? Let's say you want to rotate two balls in your hand, how d….
0
49
0
RT @TrackingPlumes: Are you interested in motor skills, musculoskeletal control and reinforcement learning? .Check out our manuscript: http….
0
18
0
RT @paul_masset: How can animals learn from rewards across timescales? Our work with @pablo_tano8 @HyungGoo_Kim @AtharNMalik @pouget_alex @….
biorxiv.org
To thrive in complex environments, animals and artificial agents must learn to act adaptively to maximize fitness and rewards. Such adaptive behavior can be learned through reinforcement learning[1...
0
31
0
RT @paul_masset: Hey #SfN23 ! Want to hear about temporal representations, dopamine and reinforcement learning? Come see our poster TT26 on….
0
9
0
RT @DavidCRowland: Major breakthrough in recovery from paralysis! With the aid of brain-spine interface, this patient was able climb steps….
nature.com
Nature - A reliable digital bridge restored communication between the brain and spinal cord and enabled natural walking in a participant with spinal cord injury.
0
74
0
Amazing work from @chiappa_alberto and the @amathislab !. Robust locomotion is made possible by an attention mechanism that gates the proprioceptive state history of the agent's joints.
#NeurIPS2022.How is the brain's motor behavior robust despite morphological changes to the body?. arxiv: website: @chiappa_alberto, @a_marinvargas and @TrackingPlumes . A thread 🧵 (1/N):
0
0
5
RT @paul_masset: In San Diego for #SfN22 ! Looking forward to presenting "a distributional code for learning across timescales in dopamine….
0
4
0
It has been an absolute pleasure collaborating with @amathislab on this fun project!. Very grateful to work with some awesome colleagues @chiappa_alberto, @nisheet0, @pouget_alex and @TrackingPlumes.
Another #MyoChallenge top-submission for the `Baoding Ball` Task. This time from the stiff_fingers team (@pablo_tano8 @chiappa_alberto @nisheet0 @pouget_alex @TrackingPlumes) ! 1 week until the end of phase 1! 🏃
0
0
8
RT @MyoChallenge: Another #MyoChallenge top-submission for the `Baoding Ball` Task. This time from the stiff_fingers team (@pablo_tano8 @ch….
0
11
0
RT @mptouzel: Enjoying the BCCN neuroAI workshop on RL today. @jdrugowitsch showed ongoing work trying to discriminate different codes from….
0
2
0
RT @mptouzel: Is this new 👀preprint👀 worth your time?. that depends on what your time is worth! . TL;DR.We ask how time’s value is encode….
0
8
0
Eight amazing speakers are presenting their ideas on Distributed Representations in RL and the brain on September 21. Very happy to organize this satellite workshop at @BernsteinNeuro with @paul_masset.
🚨Mark the date September 21: @pablo_tano8 and I are organizing a satellite workshop at the online @BernsteinNeuro conference: “Distributed Representations in #RL: from #AI to #Dopamine”. More details here:
0
0
5
Very cool: multi-timescale learning in spiking networks improves performance and robustness in tasks with strong temporal structure.
Have you ever wondered why neurons are like snowflakes? No two alike, even if they're the same type. In our latest preprint, we think we have (at least part of) the answer: it promotes robust learning. Tweeprint follows (1/16).
0
0
3
RT @Hidenori8Tanaka: Q. Can we solve learning dynamics of modern deep learning models trained on large datasets?.A. Yes, by combining symme….
0
176
0