cool-RR
AI Safety Researcher at Tufts University · ALTER AI Safety alumnus · Scientific Council Member at IAEAI · Fellow of the @psf
Tufts UniversityTel-Aviv, Israel
Pinned Repositories
GarlicSim
Pythonic framework for working with simulations.
git-cascade
Two extension scripts for merging in Git
marley
A framework for multi-agent reinforcement learning.
PySnooper
Never use print for debugging again
python_toolbox
A collection of useful Python tools
flax
Flax is a neural network library for JAX that is designed for flexibility.
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
cpython
The Python programming language
PythonTurtle
A learning environment for Python suited for beginners and children, inspired by Logo.
POLA
cool-RR's Repositories
cool-RR/PySnooper
Never use print for debugging again
cool-RR/python_toolbox
A collection of useful Python tools
cool-RR/cute-wing-stuff
A collection of scripts for Wing IDE
cool-RR/aiwatch
Website to track people, organizations, and products (tools, websites, etc.) in AI safety
cool-RR/backtick-text-selector
Obsidian plugin for selecting text in backticks
cool-RR/cool-RR
cool-RR/fruit_slots
An experiment in implicit communication between learning agents
cool-RR/obsidian-releases
Community plugins list, theme list, and releases of Obsidian.
cool-RR/pycid
Library for graphical models of decision making, based on pgmpy and networkx
cool-RR/spanreed
A *personal* personal assistant
cool-RR/stubborn
Stubborn: An Environment for Evaluating Stubbornness between Agents with Aligned Incentives
cool-RR/visidata
A terminal spreadsheet multitool for discovering and arranging data
cool-RR/JaxMARL
Multi-Agent Reinforcement Learning with JAX
cool-RR/autogen
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
cool-RR/bsuite
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
cool-RR/chatarena
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
cool-RR/chicken-coop
Emergent Dominance Hierarchies in Reinforcement Learning Agents
cool-RR/client-python
Python client library for Mistral AI platform
cool-RR/concordia
A library for generative social simulation
cool-RR/emotions_courtship
cool-RR/flax
Flax is a neural network library for JAX that is designed for flexibility.
cool-RR/gymnax
RL Environments in JAX 🌍
cool-RR/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
cool-RR/pax
Multi-Agent Experiments in JAX
cool-RR/POLA
cool-RR/purejaxrl
Really Fast End-to-End Jax RL Implementations
cool-RR/skglm
Fast and modular sklearn replacement for generalized linear models
cool-RR/sparse-ho
Fast hyperparameter settings for non-smooth estimators:
cool-RR/visidata-plugins
Custom plugins for https://github.com/saulpw/visidata/
cool-RR/zig
General-purpose programming language and toolchain for maintaining robust, optimal, and reusable software.