Danielhp95

Regym

gym-kuhn-poker

Kuhn poker implemented in accordance to OpenAI gym interface

gym-connect4

An OpenAI Gym implementation of the famous Connect 4 environment

gym-rock-paper-scissors

Rock Paper scissors environment for OpenAI Gym environment

nix-stable-diffusion

Nix-friendly fork of: Optimized Stable Diffusion modified to run on lower GPU VRAM

tmpclone-nvim

Nvim plugin to temporarily clone github repos to browse them under nvim

on-opponent-modelling-in-expert-iteration-code

Code for the paper "On opponent modelling in expert iteration"

reinforcement-learning-literature-review

Literature review for 1st year PhD

GGJ-2020-cool-game

Game coded in Global Game Jam 2020. Used in autobalancing paper!

imagine.nvim

Neovim plugin to integrate text-to-image models.

tog-paper-visualizations

Visualizations for a research paper on Self-play multiagent reinforcement learning. Visualizations thanks to streamlit

beamer-hacker-template

Hacker template for LaTeX beamer presentations

dotfiles

Configuration files for tmux, terminal, vim

ml-agents

Unity Machine Learning Agents Toolkit

nix-on-droid-config

home manager configuration for nix-on-droid

vaporwave-bullethell

Vaporwave bullethell game for IGGI.

ai-in-games-mcts

Talk and tutorial about Monte-Carlo-Tree-Search and its applications inside of the video games industry.

danielhp95.github.io

Blog about reinforcement learning and AI in videogames.

gym

A toolkit for developing and comparing reinforcement learning algorithms.

Gym-FightingICE

Official gym API for game FightingICE.

gym-go

A text-based go game written in python

home-manager-config

Home manager config for my systems

kmbeamer

My themes for Beamer.

linux-environment-setup

Installs various packages that I personally use on my everyday programming life. Thus, I can just clone this project and use any out of the box ubuntu distro as if it were my very own.

mopo

Code for MOPO: Model-based Offline Policy Optimization

nix-config

Diggah configuration file for nix

nvim-nix

Nix flake containing my neovim configuration

open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

pepper-social

This repository contains the research project that enables the robot to automatically join a group based on the modeled personal, social and public spaces of the group using deep reinforcement learning.

vim-airline-themes

A collection of themes for vim-airline