NikeHop

android_env

RL research on Android devices.

cog_process_sim

Small framework for simulations of the self-serving bias

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))

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.

PyDSRL

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

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"

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))

NikeHop/PyDSRL

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

NikeHop/android_env

RL research on Android devices.

NikeHop/cog_process_sim

Small framework for simulations of the self-serving bias

NikeHop/deepul

NikeHop/homework_fall2019

NikeHop/Minigrid

Simple and easily configurable grid world environments for reinforcement learning

NikeHop/overcooked_ai

A benchmark environment for fully cooperative human-AI performance.

NikeHop/s2orc-doc2json

Parsers for scientific papers (PDF2JSON, TEX2JSON, JATS2JSON)

NikeHop/SPACE

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