Today at the #RLDM2022 poster session @CarloDeramo will present our work on efficient task sampling for multitask reinforcement learning!.Check out how the directed sampling of informative tasks and knowledge sharing leads to the accelerated learning of more tasks!

i met my wonderful former undergrad research intern @AnnHuang42 for the first time IN THE FLESH at #RLDM2022 🥹🥹🥹

the graceful @Sandra_RoPi developed a model of optimism and pessimism biases in value prediction! she showed how baseline DA is a candidate mechanism for these biases and is often altered in psychiatric disease #RLDM2022

It's happening!! #RLDM2022

If you are attending #RLDM2022 check out today our poster on #ReinforcementLearning for Robot Assembly. 🤖🧱. @n_w_funk will be there to tell you all about our work on bringing GNN-RL to Long-horizon Robot Decision-Making!

using hierarchical Bayesian methods to fit cognitive RL models is more popular than ever!!🔥 Friday @ #RLDM2022 come learn how model development work is **critical** for success in making Bayesian versions of complex cognitive models, like our RL+WM model! @Anne_On_Tw #2.158

इस पंचायत का ये प्रस्ताव है, हम मांग करते हैं कि 4 साल की ये नौकरी हमें स्वीकार नहीं, सरकार इस योजना को वापस ले और हमें नई ठोस भर्ती दे।. - चौधरी जयन्त सिंह जी #YuvaPanchayat #बिजनौर #rldm2022.@jayantrld @RLDparty

Looking forward to #RLDM2022! I'm heading up tomorrow to present "Policy Optimization with Distributional Constraints: An Optimal Transport View".

इस पंचायत का ये प्रस्ताव है, हम म���ंग करते हैं कि 4 साल की ये नौकरी हमें स्वीकार नहीं, सरकार इस योजना को वापस ले और हमें नई ठोस भर्ती दे।. - चौधरी जयन्त सिंह जी #YuvaPanchayat #बिजनौर #rldm2022

इस पंचायत का ये प्रस्ताव है, हम मांग करते हैं कि 4 साल की ये नौकरी हमें स्वीकार नहीं, सरकार इस योजना को वापस ले और हमें नई ठोस भर्ती दे।. - चौधरी जयन्त सिंह जी #YuvaPanchayat #बिजनौर #rldm2022 .@jayantrld @RLDparty

So excited for #RLDM2022 and Saturday's #RLasAgency workshop, organized with the amazing @aharutyu + @dabelcs 🤩🤩. We'll be discussing the limits+possibilities of RL as a model of agency in cog sci/neuro/philosphy/AI with a brilliant group of scholars.

So excited for #RLDM2022! Three years is too long. Starting strong: the Twitter-less Angela Langdon giving an excellent tutorial on behavior, brain and RL. State representations matter, are different across animals, and can't be just assumed to align with experimenter's view

Come and check out our posters with work by @DavideGhez, @AtaBK, @zreagh, and @wouterkool tomorrow from 4:30-7:30pm during Poster Session 1 at #RLDM2022!!

Wonderful to talk to lots of people from both computational psychology and AI/RL backgrounds @ #RLDM2022. Pleased to have presented a causal inference model of idealisation and devaluation, work with @RyanSmith_LIBR @M_Moutoussis

Just had my first in-person poster @ #RLDM2022 convincing people that maybe anxious and depressed individuals don't just explore randomly but they actually strive to reduce their uncertainty. Work done with @toby_wise and @cpilab

Compositionality decomposed: how do neural networks generalise? . Amy Zhang discuss the key challenges ahead in Deep RL at #RLDM2022

Josh Tenenbaum on more human inspired Reinforcement Learning at #RLDM2022 @BrownUniversity.

Reinforcement learning fanboying + asking serious questions of the reward hypothesis yesterday at #RLDM2022. (Rich is much more chill about the reward hypothesis than much of the official announcements)

If you're interested in sample efficient RL and MDP homomorphisms then come to my poster today at #RLDM2022. "a simple approach to state action abstraction" at poster 2.128. This is in collaboration with Matthew Sargent, @AndreaBanino, @caswellcaswell and Lewis Griffin.

Another day at #RLDM2022 and another poster talking about Dead-ends in offline RL! I'm excited to debut some of our initial attempts to ensure more robust risk estimation via distributional RL w/ Sonali Parbhoo and @MarzyehGhassemi