NikeHop

CSRL

Code for the experiments of the paper: "Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods" (https://arxiv.org/pdf/2201.12126.pdf))

PyDSRL

Faithful Python implementation of the paper "Towards Deep Symbolic Reinforcement Learning" by Garnelo et al.

android_env

RL research on Android devices.

cog_process_sim

Small framework for simulations of the self-serving bias

deepul

homework_fall2019

Minigrid

Simple and easily configurable grid world environments for reinforcement learning

overcooked_ai

A benchmark environment for fully cooperative human-AI performance.

s2orc-doc2json

Parsers for scientific papers (PDF2JSON, TEX2JSON, JATS2JSON)

SPACE

Official PyTorch implementation of "SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition"