samlobel

RaCT_CF

Ranking-Critical Training for Collaborative Filtering

CFN

Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023

optimistic-init

Accompanying code for "Optimistic Initialization for Exploration in Continuous Control"

InfinitePhoto

A picture within a picture within picture

onager

Lightweight python library for launching experiments and tuning hyperparameters, either locally or on a cluster

simple_rl_mbrl

Simple-RL forked MBRL

spider-sim

Simulating a Spider catching its prey

adxgame

Implementation of the AdxGame.

cleanrl_starter

CleanRL set up with logging etc

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

GAILA

grad-cnns

Code and manuscript for "Efficient Per-Example Gradient Computations in Convolutional Neural Networks"

grl

gym

A toolkit for developing and comparing reinforcement learning algorithms.

launchpad

many_gamma

What do you do with value estimates at a variety of gammas?

mrl

pfrl

PFRL: a PyTorch-based deep reinforcement learning library

pytorch-utils

Code snippets in PyTorch I've found useful

q_functionals

Accompanying code for "Q-Functionals for Value-Based Continuous Control"

RBFDQN

rl_scaffolding

A framework structured the way I like, that I can branch off of for new experiments

rpc4django

RPC4Django is an XMLRPC and JSONRPC server for Django powered projects. Simply plug it into any existing Django project and you can make your methods available via XMLRPC and JSONRPC. This project is actively seeking maintainers.

samlobel.github.io

Jekyll webage

simple_rl

A simple framework for experimenting with Reinforcement Learning in Python.

skill-chaining

Implementation of "Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining"

spelling_bee

A little script to get the highest-scoring set of letters in NYTimes spelling bee

SQL-Rank

A Novel Listwise Collaborative Ranking Algorithm published at ICML'18

torchbeast

A PyTorch Platform for Distributed RL

Torchelie

Torchélie is a personal set of utility functions and layers for PyTorch.