Pinned Repositories
AsymmPlay
MarvinGPT
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
cicero
running cicero on google colab
concordia
A library for generative social simulation
diplomacy_cicero
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
Melting-Pot-Contest-2023
meltingpot
A suite of test scenarios for multi-agent reinforcement learning.
mml-book.github.io
Companion webpage to the book "Mathematics For Machine Learning"
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
sandguine's Repositories
sandguine/concordia
A library for generative social simulation
sandguine/Melting-Pot-Contest-2023
sandguine/meltingpot
A suite of test scenarios for multi-agent reinforcement learning.
sandguine/alpaca-lora
Instruct-tune LLaMA on consumer hardware
sandguine/distributional-sr
Official implementation of the Ξ΄-model presented in the paper "A Distributional Analogue to the Successor Representation".
sandguine/effective-horizon
Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"
sandguine/fast-marl
FAST iteration of MARL research ideas: A starting point for Multi-Agent Reinforcement Learning
sandguine/hanabi.github.io
A list of Hanabi strategies
sandguine/hidden-context
Code and data for the paper "Understanding Hidden Context in Preference Learning: Consequences for RLHF"
sandguine/icvf_release
Public code for "Reinforcement Learning from Passive Data via Latent Intentions"
sandguine/JaxMARL-minimal-information
Multi-Agent Reinforcement Learning with JAX
sandguine/lab2d
A customisable 2D platform for agent-based AI research
sandguine/maddpg
Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
sandguine/Mava
π¦ A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
sandguine/maxtext
A simple, performant and scalable Jax LLM!
sandguine/Meta-TTS
Official repository of https://doi.org/10.1109/TASLP.2022.3167258. More up-to-date code is in "refactor" branch.
sandguine/micrograd
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
sandguine/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
sandguine/Neural-Network-Zero-to-Hero
Writing keys libraries and core architectures from scratch. Following the tutorials of Neural Network Zero to Hero class from Andrej Karphathy.
sandguine/nn-zero-to-hero
Neural Networks: Zero to Hero
sandguine/overcooked_ai
A benchmark environment for fully cooperative human-AI performance.
sandguine/paper-reviewer-matcher
Linear programming solver for paper-reviewer matching and mind-matching
sandguine/pax
Scalable Opponent Shaping Experiments in JAX
sandguine/purejaxrl
Really Fast End-to-End Jax RL Implementations
sandguine/pycid
Library for graphical models of decision making, based on pgmpy and networkx
sandguine/ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
sandguine/redpoint_hacks
sandguine/rliable
[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.
sandguine/SAELens
Training Sparse Autoencoders on Language Models
sandguine/Voyager-Contracts
CAIF