PascalPolygon (Pascal Dao) · GitHub
Skip to content
View PascalPolygon's full-sized avatar
🤙
This will not suffice
🤙
This will not suffice
  • Melbourne, FL

Block or report PascalPolygon

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
PascalPolygon/README.md
  • 👋🏿 Hi, I’m @PascalPolygon
  • My Website
  • 👀 I’m interested in goal-directed planning for RL, Mobile Ad-Hoc Networks (MANET), 3D printing, and Jujitsu 🤙🏿 !
  • 🌱 I have a PhD in Computer Engineering at Florida Institute of Technology
  • 💞️ I’m looking to collaborate on ML projects
  • 📫 You can reach me at pdao2015@my.fit.edu

Pinned Loading

  1. trl trl Public

    Transformer Reinforcement Learning Library based on Hugging face's trl (https://github.com/huggingface/trl/tree/main/trl). Customized for adding intrinsic curiosity to GRPO advantages.

    Python 1

  2. stm32_bitbang_i2c stm32_bitbang_i2c Public

    Library to implement I2C on any GPIO for STM32 MCU's. (I2C implemented in software)

    C 24 5

  3. grpo-vdr grpo-vdr Public

    Group Relative Policy Optimization with (group) variational disagreement reward (bonus)

    Python

  4. Deep-Hierarchical-Active-Inference Deep-Hierarchical-Active-Inference Public

    Implementation of Hierarchical Active Inference Agent for perception, planning and action in OpenAI gym environments

    Python 1