Skip to content
View Arahan-kujur's full-sized avatar

Block or report Arahan-kujur

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
Arahan-kujur/README.md

Hi, I'm Arahan Kujur πŸ‘‹

πŸ‘Ά 15 πŸŽ“ High School Student | Aspiring AI Researcher & Game Developer
πŸš€ Interested in Artificial Intelligence, Reinforcement Learning, and Game Development
🧠 Currently learning C++, Python, Unreal Engine, and Machine Learning

About Me

  • Building AI and game development projects from scratch
  • Exploring Multi-Agent Reinforcement Learning and emergent communication
  • Passionate about combining AI + interactive simulations
  • Working toward a future career in Artificial Intelligence research

πŸ“š Research Projects

MARL Emergent Communication

πŸ”— https://github.com/Arahan-kujur/marl-emergent-communication

A research framework exploring emergent communication in Multi-Agent Reinforcement Learning environments.
The project investigates how agents develop communication protocols under cooperation, competition, and uncertainty using reinforcement learning methods inspired by public-goods game dynamics and signaling theory.

Premature Commitment Paper

πŸ”— https://github.com/Arahan-kujur/premature-commitment-paper

Research investigating premature convergence and commitment behaviors in learning agents and decision systems.
The work studies how early policy locking affects long-term adaptability, generalization, and exploration efficiency in intelligent systems.

Interpretability Under Distribution Shift

πŸ”— https://github.com/Arahan-kujur/interpretability-under-shift

Research project studying model interpretability when machine learning systems encounter distributional or environmental shifts.
The goal is to analyze reliability and explanation stability when models operate outside training conditions.

Choice Between Partial Trajectories Reproduction

πŸ”— https://github.com/Arahan-kujur/choice-between-partial-trajectories-reproduction

A research-oriented reinforcement learning study examining agent decision-making when only partial trajectory information is available.
The project explores behavioral reconstruction and preference learning from incomplete observations.

πŸš€ Engineering & System Projects

Aegis Core

πŸ”— https://github.com/Arahan-kujur/aegis-core

Core system architecture for experimental intelligent-agent infrastructure focused on modularity, safety, and scalable decision pipelines.
Designed as a foundational framework supporting secure agent interaction and extensible AI experimentation environments.

Argus Core

πŸ”— https://github.com/Arahan-kujur/argus-core

Monitoring and analysis subsystem designed to complement intelligent agent frameworks by enabling observation, evaluation, and system-level diagnostics.
Focused on tracking agent behavior, performance signals, and runtime interpretability.


πŸ”§ Tech Stack

Languages

  • Python
  • C++

Areas of Interest

  • Artificial Intelligence
  • Reinforcement Learning
  • Game Development
  • Simulation Systems

πŸ“« Connect With Me


⭐ Always building, always learning.

Pinned Loading

  1. aegis-core aegis-core Public

    Python

  2. argus-core argus-core Public

    Python

  3. choice-between-partial-trajectories-reproduction choice-between-partial-trajectories-reproduction Public

    Python

  4. interpretability-under-shift interpretability-under-shift Public

    Python

  5. premature-commitment-paper premature-commitment-paper Public

    Python

  6. hive hive Public

    Forked from aden-hive/hive

    Outcome driven agent development framework that evolves

    Python