mbchang

mbchang/NRI

Neural relational inference for interacting systems - pytorch

mbchang/hri

mbchang/magical

The MAGICAL benchmark suite for robust imitation learning (NeurIPS 2020)

mbchang/dreamer-pytorch

Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.

mbchang/dreamer

Dream to Control: Learning Behaviors by Latent Imagination

mbchang/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).

mbchang/KNNRegression

In this project we will be solving KNN Regression problem from scratch. We will be implementing the KNN problem in the naive method using a for loop and also in a vectorised approach using numpy broadcasting. We will also plot the root mean squared error for various K values and chose the optimal number of nearest neighbours.

mbchang/G-SWM

Official PyTorch implementation of "Improving Generative Imagination in Object-Centric World Models"

mbchang/pytorch-vqvae

Vector Quantized VAEs - PyTorch Implementation

mbchang/causal_graphs

mbchang/AlphaNPI

mbchang/craft-env

mbchang/o2p2

mbchang/classification_starter_code

mbchang/ARS

An implementation of the Augmented Random Search algorithm

mbchang/OP3

mbchang/video-annotation

Quickly annotate videos with bounding boxes for use in training object detectors and trackers.

mbchang/maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

mbchang/mnist_transforms

mbchang/multiworld

Multitask Environments for RL

mbchang/babyai

BabyAI platform. A testbed for training agents to understand and execute language commands.

mbchang/rl-starter-files

RL starter files in order to immediatly train, visualize and evaluate an agent without writing any line of code

mbchang/gym-minigrid

Minimalistic gridworld environment for OpenAI Gym

mbchang/torch-ac

Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms: A2C and PPO

mbchang/PyTorch-RL

PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.

mbchang/Relational-NEM

Code for the "Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions" paper.

mbchang/ee227c.github.io

EE227C (Spring 2018) Course page

mbchang/cf

mbchang/awesome-deep-learning-papers

The most cited deep learning papers

mbchang/6.945-physics