Skip to content
@uam-rl

uam-rl

Project Icon

UAM Reinforcement Learning Projects

Servicio Social - Universidad Autónoma Metropolitana

Roadmap

  • Torch-RL with OpenAI Gym: Build foundational RL models using PyTorch and Gymnasium (formerly OpenAI Gym)
  • Atari Game Agent: Develop an RL system for classic Atari games
  • Transformer-based RL: Explore RL projects integrating transformer architectures

Research Focus

We're particularly interested in:

  • GRPO (Group Relative Policy Optimization): The efficient RL algorithm popularized by DeepSeek that eliminates the need for a separate critic model, reducing memory and compute overhead by ~50% compared to traditional PPO
  • LoRA Fine-tuning: Using Low-Rank Adaptation to efficiently fine-tune base models with reinforcement learning

References

Popular repositories Loading

  1. .github .github Public

  2. uam-rl.github.io uam-rl.github.io Public

    Typst

  3. state-of-rl-mid-2025 state-of-rl-mid-2025 Public

    State of Reinforcement Learning - Mid 2025 Overview

  4. state-of-rl-late-2025 state-of-rl-late-2025 Public

    State of Reinforcement Learning - Late 2025 Overview

    Typst

  5. deepseek-r1-grpo deepseek-r1-grpo Public

    Typst

Repositories

Showing 5 of 5 repositories

Top languages

Loading…

Most used topics

Loading…