Enabling constructive dialogue.

utilities for decoding deep representations (like sentence embeddings) back to text

Extract full next-token probabilities via language model APIs

The Nomyx game

Governance of the Commons Simulation (GovSim)

Generative Agents: Interactive Simulacra of Human Behavior

course homepage for Introduction to Machine Learning

Dataset to propose for TidyTuesday

A lightweight research framework

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Code and data for our IROS paper: "Are Large Language Models Aligned with People's Social Intuitions for Human–Robot Interactions?"

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

An index of algorithms for reinforcement learning from human feedback (rlhf))

Language model alignment-focused deep learning curriculum

An API conversion tool for popular external reinforcement learning environments

creating agents with normative reasoning ability

A simple altar game based on Phaser3

Maximum diversity problem solver in Python using a genetic algorithm

This is the official implementation of Multi-Agent PPO (MAPPO).

A Python library for dynamic classifier and ensemble selection

A library for generative social simulation

Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"

Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]

Harvard Joint CS + Government Thesis Project 2018-2019: Escaping the State of Nature

hanabi_learning_environment is a research platform for Hanabi experiments.

This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.