Manfred Diaz

awesome-autonomous-vehicles. Curated List of Self-Driving Cars and Autonomous Vehicles Resources

berkeley-cs-188. Berkeley CS 188 Artificial Intelligence [Projects Work]

deep-learning-pi3. Pytorch Pre-trained CNN Models Benchmark on Raspberry Pi 3

openal-android-sample. A working sample of openal4android library.

duckietown_dtp. Detection, Tracking and Prediction in Duckietown

deep-docker. Dockerfile for creating a docker image with default configurations for Deep Learning tasks

rl-benchmarks. A Historic Recollection of Reinforcement Learning Benchmarks

homework. Assignments for CS294-112.

mechanics-curriculum-src. This repository accompanies the paper "Rethinking Teacher-Student Curriculum Learning through The Cooperative Mechanics of Experience"

marlgrid. Gridworld for MARL experiments

ecotheory. An Information Theory Perspective on the Complexity of MDPs

selfdrivingcar-engineer-nd. Udacity's Self-Driving Car Nanodegree Program Work

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

manuscripts. Archive of Published / Submitted Manuscripts

multigym. Python

gym-duckietown. Self-driving car simulator for the Duckietown universe

gym-miniworld. Simple 3D interior simulator for RL & robotics research

MARL-Papers. Paper list of multi-agent reinforcement learning (MARL)

multiagent-particle-envs. Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

safe-iil. Python

cnn-traffic-light-evaluation. A short evaluation of CNN architectures/papers for German Traffic Sign Recognition Benchmark (GTSRB)

cs344. Introduction to Parallel Programming class code

pac-simulator. Pacman Driving Simulator

vae_tensorflow. Implementation of generative models from the Variational AutoEncoders family on Tensorflow

pic. "Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning"(https://arxiv.org/abs/2103.12726)

distributed-systems. Concordia COMP 6231 Distributed Systems Design Final Project

old-profile. Personal Website

manfreddiaz.github.io. A beautiful, simple, clean, and responsive Jekyll theme for academics

url_benchmark. Python

duckuments. All duckuments and the Duckietown book.

COMP417_Fall2019. HTML

spinningup. An educational resource to help anyone learn deep reinforcement learning.

CarND-Transfer-Learning-Lab. Python

rl-laplacian. Learning Laplacian Representations in Reinforcement Learning

TD3. PyTorch implementation of TD3 and DDPG for OpenAI gym tasks

nn-autoencoder-classification. Train Stacked Autoencoders for Image Classification

challenge-aido1_LF1-lane-controller-baseline. Tune your own lane controller parameters for the lane following AI-DO challenge

krrish94.github.io. My homepage

CarND-Advanced-Lane-Lines. Python

active-domainrand. Code repository for Active Domain Randomization (CoRL 2019, https://arxiv.org/abs/1904.04762)

spectral_inference_networks. Implementation of Spectral Inference Networks, ICLR 2019

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

brax. Massively parallel rigidbody physics simulation on accelerator hardware.

rwg-benchmark. Analyzing Reinforcement Learning Benchmarks with Random Weight Guessing

gym-minigrid. Minimalistic gridworld package for OpenAI Gym

graph_nets. Build Graph Nets in Tensorflow