alexlee-gk

video_prediction

Stochastic Adversarial Video Prediction

slac

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model

lpips-tensorflow

Tensorflow port for the Learned Perceptual Image Patch Similarity (LPIPS) metric.

visual_dynamics

Learning visual servoing with deep features and fitted Q-iteration

citysim3d

CitySim3D: Simulated car following benchmark

cs150

UC Berkeley CS150 Final Project: Face Tracking and Real-Time Ray Tracing implemented in a FPGA

PerceptualSimilarity

Learned Perceptual Image Patch Similarity (LPIPS) metric. In CVPR, 2018.

mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

shape_pusher_env

Simple mujoco environment of a sphere agent pushing objects of various shapes and colors

deepflite

DEEPFLITE: Direct End-to-End Perceptive Flight Learning in Tactical Extremes

agents-1

TF-Agents is a library for Reinforcement Learning in TensorFlow

alexlee-gk.github.io

caffe

Caffe: a fast open framework for deep learning.

dm_control

The DM Control Suite and Package is a tool for developing and testing reinforcement learning agents for the MuJoCo physics engine.

ee227bt-report

EE227BT Final Project Report

gym

A toolkit for developing and comparing reinforcement learning algorithms.

jasper-client

Client code for Jasper voice computing platform

Lasagne

Lightweight library to build and train neural networks in Theano

lsdc

models

Models built with TensorFlow

pix2pix-tensorflow

Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/

PlaNet

Deep Planning Network: Control from pixels by latent planning with learned dynamics

probability

Probabilistic reasoning and statistical analysis in TensorFlow

rapprentice

Rapprentice: software for teaching robots by example

scikits.cuda

CUDA SciKit

tensorflow

Computation using data flow graphs for scalable machine learning

Theano

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

trajopt

Trajectory Optimization

video_prediction-1

Stochastic Adversarial Video Prediction https://video-prediction.github.io/video_prediction

video_prediction_tables