aslansd Goto Github PK

modified-ai-economist-wt

Modified AI-Economist with Teaching: A Multi-agent Reinforcement Learning Study of Evolution of Teaching under Libertarian and Utilitarian Governing Systems

multi-agent-emergence-environments

Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"

multiagent

Using RLLib and PycoLab to explore intelligent cooperative behavior in sequential social dilemmas

multimodalencoding

neuroinspired-vision

Trade-off among Over-parameterization, Disentanglement, and Dimensionality in Neural Networks

nlsom

🤯 Mindstorm in Natural Language-based Societies of Mind

omni

OMNI: Open-endedness via Models of human Notions of Interestingness

opengpts

open_flamingo

An open-source framework for training large multimodal models

pags

Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness (Neurips 2023)

phantom

A Multi-agent reinforcement-learning simulator framework.

pizza

Code repository for "The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks"

playground_env

Implementation of the Playground environment from the paper Language as a Cognitive Tool to Imagine Goals inCuriosity-Driven Exploration.

prismer

The implementation of "Prismer: A Vision-Language Model with An Ensemble of Experts".

prospective-configuration

This repository contains the code for the paper "Inferring Neural Activity Before Plasticity: A Foundation for Learning Beyond Backpropagation."

pyglmhmm

A Python implementation of GLM-HMM

rair-mbrl

Code for our NeurIPS 2023 Paper: Regularity as Intrinsic Reward for Free Play

rl_abstraction

Code for experimenting with state and action abstractions in reinforcement learning.

rl_info_theory

A collection of code investigating the use of information theory for abstractions in RL

robotic-warehouse

Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment

robust_representation_similarity

Understanding robust learning through the lens of representation similarity

rode

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.

roma

Codes accompanying the paper "ROMA: Multi-Agent Reinforcement Learning with Emergent Roles" (ICML 2020 https://arxiv.org/abs/2003.08039)

sample_efficient_pop_codes

sensorium_2023

repo for the sensorium 2023 competition

sequential_social_dilemma_games

Repo for reproduction of sequential social dilemmas

shap

A game theoretic approach to explain the output of any machine learning model.

shapley

The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).

simple_rl

A simple framework for experimenting with Reinforcement Learning in Python.

spatio-temporal-language-transformers

Code for the paper Grounding Spatio-Temporal Language with Transformers