mzhao98

ActiveLearning_ImageClassification

Active Learning for Multiclass Image Classification on Fruits360 Dataset

Motion-Magnification

Implementation of Phase-Based Video Motion Processing (Wadhwa et al. 2013)

pose-estimation

Action Recognition with Pose Estimation

laplacian_blend

Tutorial on Laplacian Image Blending

emotion_recognition

CMU 10-701: Facial Expression Recognition on https://www.kaggle.com/msambare/fer2013

text-summarization

Extractive vs. Abstractive Text Summarization Methods

DeepQLearning_CrossyRoad

Deep Q Learning for learning Crossy road and Frostbite games

MultiresolutionGAIL_Baselines

Hierarchical Multiscale Recurrent Neural Network and Clockwork RNN implementations as baselines for comparison to a Multiresolution GAIL algorithm.

RoadTracing

ta2-dash

Trajectory Replay Dashboard: DARPA ASIST TA2

mzhao98/model_recon

mzhao98/awesome-social-agents

A collection of works that investigate social agents, simulations and their real-world impact in text, embodied, and robotics contexts.

mzhao98/robomimic

robomimic: A Modular Framework for Robot Learning from Demonstration

mzhao98/mzhao98.github.io

Github personal website

mzhao98/diffusion_policy

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

mzhao98/conformal-time-series

Conformal prediction for time-series applications.

mzhao98/basic-quantile-regression

Example of using Quantile Regression for Instacart ETAs

mzhao98/meltingpot

A suite of test scenarios for multi-agent reinforcement learning.

mzhao98/repeated-shared-autonomy

project on shared autonomy with repeated interactions

mzhao98/DDPG-HER

Implementation of the Deep Deterministic Policy Gradient and Hindsight Experience Replay.

mzhao98/mutual-irl

Mutual Inverse Reinforcement Learning

mzhao98/POMDPy-Declutter

POMDPs in Python.

mzhao98/stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

mzhao98/PantheonRL

PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.

mzhao98/ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.

mzhao98/MARLlib

The MARL extension for RLlib. A benchmark for research and industry.

mzhao98/virtualhome_unity

Source Code for VirtualHome environment

mzhao98/pomdp-py

A framework to build and solve POMDP problems. Documentation: https://h2r.github.io/pomdp-py/

mzhao98/watch_and_help

Code for the paper Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

mzhao98/sequential_social_dilemma_games

Repo for reproduction of sequential social dilemmas

mzhao98/virtualhome_userinterface

Interface to interact with VirtualHome via browser

mzhao98/CleanUp-Tasks

mzhao98/16831-Spring-2022

mzhao98/cqr

Conformalized Quantile Regression

mzhao98/baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

mzhao98/overcooked-hAI-exp

Overcooked-AI Experiment Psiturk Demo (for MTurk experiments)

mzhao98/hindsight-experience-replay

This is the pytorch implementation of Hindsight Experience Replay (HER) - Experiment on all fetch robotic environments.

mzhao98/VirtualHomeWebServer

Streaming server for Unity

mzhao98/Decision-Making-Under-Uncertainty

Decision making under uncertainty using the POMDPs.jl ecosystem taught by Robert Moss

mzhao98/cogail

Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration