@lnalegre Profile picture

Lucas Alegre

@lnalegre

Working on Reinforcement Learning. Ph.D. student at @INF_UFRGS. Member of @FaramaFound. Guitarist in my spare time.

Similar User
Willem Röpke photo

@willem_ropke

Roxana Rădulescu photo

@rox_teo

Florian Felten photo

@FlorianFelten1

Peter Vamplew photo

@amp1874

Conor Hayes photo

@conorfhayes

Youri Coppens photo

@yocoppen

Pieter Libin photo

@PieterLibin

vicente photo

@gesoneeeeeeeeel

túlio photo

@randomcolorado

Tim Brys ن photo

@brys_tim

Pinned

Extremely happy to announce my first paper at @icmlconf! "Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer" code🐍- github.com/LucasAlegre/sf… video🎥- soon at #ICML2022 paper📃- arxiv.org/abs/2206.11326 1/🧵


Lucas Alegre Reposted

Monday, July 1st, the community-led RL group starts July strong with a presentation from @lnalegre on "Sample-Efficient Multi-Task and Multi-Objective Reinforcement Learning by Combining Multiple Behaviors." 😃 Learn more: cohere.com/events/cohere-…

Tweet Image 1

Lucas Alegre Reposted

🚀 The Open RL Benchmark paper is out! 📝 Open RL Benchmark is everything I love about open research: a global, decentralized and open collaboration pooling vast training data for universal benefit. github.com/openrlbenchmar… arxiv.org/abs/2402.03046

Tweet Image 1

This is result of an awesome collaboration with @FlorianFelten1 during my time at @aibrussels! Many thanks to the @FaramaFound team for all the great support :) It is great to see that this project is already being useful to many researchers working on multi-objective RL 🎉

We are thrilled to announce that MO-Gymnasium has reached mature status within the Farama Foundation! MO-Gymnasium is a multi-objective version of Gymnasium for problems in which you must learn policies for different trade-offs between multiple rewards.🧵 github.com/Farama-Foundat…



Lucas Alegre Reposted

Multiple AI Lab researchers presented their demos at the BNAIC 2022 conference. #bnaic #aidemos PhD students Lucas presented MO-Gym: a Multi-Objective Reinforcement Learning library which provides a set of benchmarks under a standardized API. Check it: github.com/LucasAlegre/mo…

Tweet Image 1

Lucas Alegre Reposted

Today with my guy @lnalegre, we were presenting MO-Gym at BNAIC. It is a Multi-Objective Reinforcement Learning library which provides a set of benchmarks under a standardized API. It is available here: github.com/LucasAlegre/mo…. 🧵⬇️

Tweet Image 1

Loading...

Something went wrong.


Something went wrong.