philipjball Goto Github PK

activeinferencenotes

🐁 Notes on active inference

aevb_vae

🔥 A custom VAE implemetation in PyTorch

arnold

Arnold - DOOM Agent

augwm

Augmented World Models

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

betatonorm

A simple function that helps to fit beta and normal distributions

brax

Massively parallel rigidbody physics simulation on accelerator hardware.

caltech-cs1156x-codes

🏫🏫🏫 Python codes I wrote to successfully complete this course. 🏫🏫🏫

cffair_emulate

⚖️ Emulate the Counterfactual Fairness (2017 Kusner et al.) results in Python

coding-template

comparing-pca-to-pat

A quick exposition into the similarities in these techniques

corl

High-quality single-file implementations of SOTA Offline RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC

datascience-pythonscripts

Some scripts I've written to expedite the data science process, WIP

digitech

Digitech 1.0.0

dmcgym

doomopenaibaselines

🔫 Using OpenAI baselines to train a VizDoom environment

dotfiles

⚫ My dotfiles repo

dqnflappy

🐤 Using DQN to learn FlappyBird

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

flappybird

A Flappy Bird Clone using python-pygame

foragingenv

Makes the foraging environment in OpenAI Gym

gensim

Topic Modelling for Humans

getstarted

🖥️ This is a list for my own use to figure out how to set things up when I use a new computer

gym-vizdoom

Gym wrapper for Vizdoom environments

hackerrank_solns

Some solutions to HackerRank/Coding Challenges

housepricetop10kaggle

🏠 Top 10% Notebook showing my approach of this dataset.

jupyter-notebook-slides

kerascntk_meme_gan

🤦 This has a working DCGAN written for Kersas+CNTK in Python2.7 and a pilfered PyTorch DCGAN

mj_envs

A collection of MuJoCo based environments.

my_cv

👨 A hacked and slashed Friggieri-style CV