Rafael Rodriguez Sanchez

PhD Student @browncsdept | Thinking about RL, Natural Language grounding and Objects | Previously @campusb and @polimi

[Benjamin Spiegel @superspeeg]

Why did only humans invent graphical systems like writing? 🧠✍️

In our new paper at @cogsci_soc, we explore how agents learn to communicate using a model of pictographic signification similar to human proto-writing. 🧵👇

[Benedict Quartey @Benedict_Q]

At #NeurIPS2023 all week presenting “Exploiting Contextual Structure to Generate Useful Auxiliary Tasks”. Hoping to chat with folks about:

- Embodied AI
- Reinforcement Learning
- Multimodal LLMs for Robot decision making
- Anything!

Please send a DM lets hang out!

[Akhil Bagaria @akhil_bagaria]

Sparse rewards got you down? Tired of tuning RND? Wanna use pseudocounts but don’t want to think about recoding probabilities? Come hang out at poster 311 at #ICML2023 at 10:30 am tomorrow 🏖️🏖️

[Rafael Rodriguez Sanchez @rafarodsa]

come talk to me and Ben Spiegel about languages, RL and knowledge representation in the age of LLMs #ICML2023 at Exhibit Hall 1 #615 on Tuesday at 11am!

[Roma Patel @996roma]

also check out @rafarodsa's paper on grounding language to components of MDPs beyond just rewards and goals: on tuesday in poster session 1!

[Jorge Mendez-Mendez @JorgeAMendez_]

We are happy to announce the release of #CompoSuite, our benchmark of #robotic manipulation tasks for studying functional #compositionality for #MultiTaskLearning and #ContinualLearning in #ReinforcementLearning!
@CoLLAs_Conf
🧵👇
https://t.co/lyurnaG2A5
https://t.co/9TS5FafDrb

[Alberto Maria Metelli @alberto_metelli]

We are excited to announce the 15th European Workshop on Reinforcement Learning #EWRL2022 that will be a physical event hosted by @polimi on 19-21 September in Milan! The #CFP is finally out at https://t.co/rnRO23FuUy. Join us to discuss the latest advancements in #RL!