ibagur

Hi there 👋

✨Some of my stuff!✨

• 🧠 Reinforcement Learning

  • Various experiments in RL using Meta-learning, Recurrent Independet Mechanisms and Hierarchical Transformer Memory
  • Tutorial fork: Policy Gradient algorithms from A2C to SAC
  • Fork of MiniGrid compatible with gym 0.21

• 🤖 LLM Agents

  • A simple searcher-evaluator with pydantic-ai
  • Using MCP tools with smolagents
  • Early RAG experiments with LangChain

• 🌍 Humanitarian Tools

  • Cholera hotspot monitoring system in R
  • RAG agent in LangChain for GBV in emergencies documentation
  • GBV Response Dashboard for Türkiye earthquake in flexdashboard
  • jupyternotebook with quick crisis analysis in North Mozambique using ACLED data
  • My portfolio of humanitarian information products

• 📝 Academic & Research

  • My master thesis in Reinforcement Learning
  • Optimization Algorithms assignments
  • Reinforcement Learning assignments

• 🧪 Experiments, Tests and Forks

  • Continual Learning via Bit-Level Information Preserving
  • Stabilizing Transformers for Reinforcement Learning
  • Self-Attention PPO Pytorch
  • BRIMS: Bidirectional Recurrent Independent Mechanisms