Hello there!

I’m a third-year student researcher at the Davis Institute for Artificial Intelligence and a Computer Science and Mathematics major. My research is centered on enhancing planning and reasoning among AI agents, with recent work exploring the integration of Reinforcement Learning (RL), Large Language Models (LLMs), and Graph Neural Networks (GNNs).

I am currently involved in the EMHAT project within the Comp-HuSim lab, focusing on developing and simulating AI agents to study cooperation and personality dynamics in interactions. My previous research was funded by DARPA and the Microsoft Foundational Model Research program.

Outside of my research, I am passionate about photography and drone building.

Dreamer Walker Brain

Recent Publications and Projects

All publications

Aug 2024 • Minh Pham Dinh, Munira Syed, Michael G Yankoski, Trenton W. Ford

ReasonPlanner: Enhancing Autonomous Planning in Dynamic Environments with Temporal Knowledge Graphs and LLMs

We introduce ReasonPlanner, a novel generalist agent designed for reflective thinking, planning, and interactive reasoning. This agent leverages Large Language Models (LLMs) to plan hypothetical trajectories by building a world model through an expert-guided walkthrough of the environment. The agent interacts with the environment using a natural language actor-critic module, where the actor translates the imagined trajectory into a sequence of actionable steps, and the critic determines if replanning is necessary.

Areas      ARTIFICIAL REASONING      NATURAL LANGUAGE PROCESSING     

Feb 2024 • Minh Pham Dinh

PyDreamerV1: Clean pytorch implementation of Hafner et al Dreamer

This project offers a comprehensive implementation of the Dreamer algorithm, as presented in the groundbreaking work by Hafner et al., "Dream to Control: Learning Behaviors by Latent Imagination." Our implementation is dedicated to faithfully reproducing the innovative approach of learning and planning within a learned latent space, enabling agents to efficiently master complex behaviors through imagination alone..

Areas      WORLD MODEL      REINFORCEMENT LEARNING     

Dec 2023 • Minh Pham Dinh

RLforDummy: Reinforcement Learning Algorithms Implementation

This project is a collection of my implementations of several key Reinforcement Learning (RL) algorithms. It serves as a practical exploration into the field of RL and demonstrates the application of these algorithms in solving complex environments.

Areas      REINFORCEMENT LEARNING