jparkerholder Goto Github PK

asebo

Code to run the ASEBO algorithm from the paper: From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization... please get in touch if interested!!

autorl.github.io

brain-tokyo-workshop

🧠🗼

bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

continual_rl

Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.

data-mining_small-caps

Using data mining techniques to classify small cap equity returns

dataviz-forum

This will serve as the public forum repository to which anyone can post. [Don't put your graded homework here!]

deep-neuroevolution

Deep Neuroevolution

dreamerv2

Mastering Atari with Discrete World Models

dvd_es

Code from the paper "Effective Diversity in Population Based Reinforcement Learning", presented as a spotlight at NeurIPS 2020. This is the Evolution Strategies implementation, but of course the method can be used for gradient based RL algorithms (e.g. TD3).

es

Simple ES implementation using ray and numpy

hanabi_sad

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

jparkerholder.github.io

offcon3

📴 OffCon^3: SOTA PyTorch SAC and TD3 Implementations (arxiv: 2101.11331)

pb2

Code for the Population-Based Bandits Algorithm, presented at NeurIPS 2020.

procgen_autorl

pytorch_notebooks

tutorial notebooks

qmss2017

Materials for the 2017 QMSS Python Workshop

ray

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

readypolicyone

🔍 Codebase for the ICML '20 paper "Ready Policy One: World Building Through Active Learning" (arxiv: 2002.02693)

rl-generalization-paper

A list of papers regarding generalization in (deep) reinforcement learning

sac-pytorch

🧶 Minimal PyTorch Soft Actor Critic (SAC) implementation

speeding-up-cnns-using-random-feature-maps

Final project for big data and machine learning.