Daniel Nguyen's Projects
The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks
Pseudo Labeling for Neural Networks and Logistic Regression/SVMs ( Based on "Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks")
Official implementation of "Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning"
Python code for "Deep Learning for Massive MIMO CSI Feedback"
Implementation of the Deep Deterministic Policy Gradient (DDPG) using PyTorch
Papers being part of the state of the art on reinforcement learning
Project regarding Resource allocation using RL
Simulated the scenario between edge servers and users with a clear graphic interface. Also, implemented the continuous control with Deep Deterministic Policy Gradient (DDPG) to determine the resources allocation (offload targets, computational resources, migration bandwidth) in the edge servers
Code for experimenting with state and action abstractions in reinforcement learning.
Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.
Returns latest research results by crawling arxiv papers and summarizing abstracts. Helps you stay afloat with so many new papers everyday.
Code for abstracting, evaluating, and visualizing Markov Decision Processes.