wjianpeng Goto Github PK

convolutional-neural-net

A Convolutional Neural Network built from scratch - Assignment for Advanced Computer Vision course at University of Michigan, Ann Arbor

ddpg

Reimplementation of DDPG(Continuous Control with Deep Reinforcement Learning) based on OpenAI Gym + Tensorflow

deep-rl

Collection of Deep Reinforcement Learning algorithms

deeplearning

Deep learning code by Hinton

deeplearning-1

deeploco

deepqlearn

Simple deep q-learning implementation. Makes use of a modified version of my q-learning script, and neural network implementation.

dnn

multi-layer feed-forward neural networks.

image-classification-using-cnn

Classification of images in CIFAR 10 dataset uding a deep convolutional neural network architecture. The backpropagation formulae have been derived for the CNN and accordingly the algorithm developed. Mini batch gradient descent is used to learn the biases and filters of the network.

matconvnet-dag

matlab2048

2048 playing agent using deep Q-learning in Matlab.

ml-agents

Unity Machine Learning Agents Toolkit

openai-cartpole

random search, hill climbing, policy gradient

pg-arm

Policy Gradient based controller for simple 2D modular arm

policy-gradient-reinforcement-learning

policy-gradient-reinforcement-learning-for-robot-model-learning

reinforcement-learning-algorithms-and-dynamic-programming

Reinforcement learning Algorithms such as SARSA, Q learning, Actor-Critic Policy Gradient and Value Function Approximation were applied to stabilize an inverted pendulum system and achieve optimal control. So essentially, the concept of Reinforcement Learning Controllers has been established. The Reinforcement Learning Controllers have been compared on the basis of performance and efficiency and they are separately compared with the classical Linear Quadratic Regulator Controller. Each of the RL controller have been integrated with a Swing up controller. A virtual switch toggles between the Swing up controller and the RL controller automatically, based on the value of the angular deviation theta with respect to the vertical plane. My research paper and my undergraduate thesis have been uploaded for reference. All the codes have also been uploaded.

reinforcement-learning-with-tensorflow

Simple Reinforcement learning tutorials

simple-neural-network

A simple Python script showing how the backpropagation algorithm works.

zhihuzhuanlan