LUKELIEM

actor-critic

Implement a single-agent actor-critic to master the Atari games.

cnn-simplicity

Design several convolutional neural network implementing "Strive for Simplicity" and Model Ensembling.

CS231N-Assignment-1

CS231N-Assignment-2

Stanford University CS231N Assignment 2 - Winter (January - March, 2016)

CS231N-Assignment-3

Stanford University CS231N Assignment 3 - Winter 2015

jetbot_visualservoing

Image based visual servoing

lead-follow

This is one component of Cross-functional Team-based Multi-agent (CTMA) framework.

team_marl

Team-based Multi-agent Reinforcement Learning

LUKELIEM/cnn-simplicity

Design several convolutional neural network implementing "Strive for Simplicity" and Model Ensembling.

LUKELIEM/jetbot_visualservoing

Image based visual servoing

LUKELIEM/team_marl

Team-based Multi-agent Reinforcement Learning

LUKELIEM/actor-critic

Implement a single-agent actor-critic to master the Atari games.

LUKELIEM/lead-follow

This is one component of Cross-functional Team-based Multi-agent (CTMA) framework.

LUKELIEM/CS231N-Assignment-1

LUKELIEM/CS231N-Assignment-2

Stanford University CS231N Assignment 2 - Winter (January - March, 2016)

LUKELIEM/CS231N-Assignment-3

Stanford University CS231N Assignment 3 - Winter 2015

LUKELIEM/deep_rl

Deep reinforcement learning using PyTorch

LUKELIEM/DQN-pytorch

A PyTorch implementation of Human-Level Control through Deep Reinforcement Learning

LUKELIEM/EKF

Implement Extended Kalman Filter on Jetbot.

LUKELIEM/Fortune-Cookie

A simple but positive Chinese Fortune Cookie Android App.

LUKELIEM/geocosmo

These are iPython notebooks and python codes developed during my internship at the startup

LUKELIEM/invest

Machine learning project for identifying 10 and 100 Baggers

LUKELIEM/jetbot-open-end-control

LUKELIEM/leader

LUKELIEM/lstm-music

Use lstm to generate ABC-annotation music

LUKELIEM/move37

Coding Demos from the School of AI's Move37 Course

LUKELIEM/multi-agent

Development code for team-based multi-agent reinforcement learning.

LUKELIEM/navigation

Implement path planning and navigation on Jetbot.

LUKELIEM/pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

LUKELIEM/pytorch_tutorial

This is a series of Notebooks to master the PyTorch AI Framework

LUKELIEM/recommender

CSE258 Recommender System

LUKELIEM/reinforce

A series of Jupyter Notebooks documenting how I learn policy-based reinforcement learning.

LUKELIEM/reinforcejs

Reinforcement Learning Agents in Javascript (Dynamic Programming, Temporal Difference, Deep Q-Learning, Stochastic/Deterministic Policy Gradients)

LUKELIEM/roboschool

Open-source software for robot simulation, integrated with OpenAI Gym.

LUKELIEM/WeatherApp

This is a simple weather forecast Android app. It is location-aware and pull forecast data from forecast.io.