Skip to content
View Sam-Oliveira's full-sized avatar
9 followers · 12 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report Sam-Oliveira

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Sam-Oliveira/README.md

Samuel Oliveira 🇵🇹 🇬🇧 🇨🇦

Hi! I'm Samuel. I'm a PhD student at the RLAI Lab at the University of Alberta 🇨🇦 . I am also affiliated with Amii.

  • 🤖 ♾️ I work on creating Reinforcement Learning agents that can learn continually and forever, without forgetting previous knowledge.
  • 💻 I mostly code in Python and PyTorch. I also have experience with SQL, Terraform, and with AWS.
  • 📚 I'm currently dabbling in Robotics and Robot Learning.
  • 📌 I'm originally from Portugal 🇵🇹
  • 🎓 I previously studied at UCL and Imperial College London 🇬🇧
  • 💡 I previously did research in the intersection of RL and diffusion models, as well as in ML applied to healthcare.
  • 📤 Reach out for any job opportunities or to discuss anything ML/AI related: samuelccoliveira at gmail dot com

Pinned Loading

  1. diffuser_irl diffuser_irl Public

    Forked from jannerm/diffuser

    Code for my MSc Thesis on learning reward models (Inverse Reinforcement Learning) with Diffusion Models.

    Python

  2. research_assistant research_assistant Public

    LLM-based web app (StreamLit) for an automated research assistant that 1) finds recent papers 2) summarizes them 3) proposes new research ideas based on recent papers.

    Python

  3. maxjappert/multi-agent_distral maxjappert/multi-agent_distral Public

    This is a repository for an implementation of DeepMind's Distral for a multi-agent setting.

    Jupyter Notebook 1

  4. pretraining_mae pretraining_mae Public

    Code for the project "Impact of the pre-training data distribution on the fine-tuned performance of Masked Autoencoders".

    Jupyter Notebook

  5. ray_tracing ray_tracing Public

    Final Coursework for the Computer Graphics module (Department of Computing) at Imperial College London

    1

  6. language_model_from_scratch language_model_from_scratch Public

    My own implementation of a Transformer-based decoder-only LM, inspired by Andrej Karpathy's video.

    Python