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