Anderson Compalas

acompalas@ucsd.edu

I am a first year MS student in the Intelligent Systems: Robotics and Control program at UC San Diego. I received a B.S. in Applied Mathematics at UC Santa Cruz in 2025. As an undergraduate at UCSC, I had the opportunity to work with Eric Wang, tutoring for his class in machine learning, and helping out with research in multi-modal AI at his lab.

Right now I am looking to pursue research in deep reinforcement learning and Vision-Language-Action models, with applications in imitation learning, dexterous manipulation, legged robotics, and humanoids.

CV  |   GitHub    

profile photo

Research

Multimodal Situational Safety


Kaiwen Zhou*, Chengzhi Liu*, Xuandong Zhao, Anderson Compalas ,Dawn Song ,Xin Eric Wang†
arXiv 2024

Webpage | arXiv | Code | BibTeX


Projects

Deep Q-Learning on LunarLander


RL Project

A reinforcement learning agent trained with Deep Q-Networks to solve the LunarLander-v2 environment.

Code | Demo

Cartpole using REINFORCE with baseline


RL Project

Implemented REINFORCE with baseline on OpenAI gym's Cartpole-v1

Code | Demo

GridWorld Exploration with TD-Learning


RL Project

Implemented and compared Tabular RL methods in a custom GridWorld with Monte Carlo control (every-visit, episodic), TD(0) SARSA (on-policy), and TD(0) Q-learning (off-policy). The project highlights differences between episodic vs. temporal-difference updates.

Code | Demo





website template