Name: Adam J. Berlier
Type: User
Company: CACI International Inc
Bio: Senior AI Research Scientist at CACI International Inc
Computer Science Ph.D. Student at UMBC studying Reinforcement Learning in Human-Robot Interaction
Twitter: ajberlier
Location: Denver, CO
Blog: https://ajberlier.github.io/
Adam J. Berlier's Projects
Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"
My personal portfolio built with Jekyll and GitHub Pages
CLIPort: What and Where Pathways for Robotic Manipulation
COVID19 data viz with Dash
This repo serves a boilerplate for anyone to quickly setup a Plotly Dash web application with updates from a database
Makefile template for docker-compose
A set of scripts and tutorials to get my team quickly up to speed on how I use Docker
Flexible-Jekyll is a simple and clean theme for Jekyll
A toolkit for developing and comparing reinforcement learning algorithms.
An OpenAI Gym environment for the SCAREcrow project
initial file for cmsc 671 fall 2020 hw7
Following the tutorials by the Intelligent Quads YouTube Channel
This repo serves a boilerplate for anyone to quickly setup a containerized web server on Linux
Multilayer Perceptron from scratch in python
This is is a multi-agent weapons scheduling Gymnasium environment with baseline command and control algorithms.
RL starter files in order to immediatly train, visualize and evaluate an agent without writing any line of code
Reinforcement Learning for Real Life (RL4RL) is a repository of reproducible experiments supporting my Ph.D. research studying reinforcement learning approaches for real-life applications.
simple path planning environment and reinforcement algorithms
This is a repo of handy tools that I use when starting new ROS projects.
Search and download Copernicus Sentinel satellite images
Tools for improving my personal software development process.
My implementation of the concepts learned from OpenAI's Spinning Up in Deep RL educational tutorial
Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO