#
Starred repositories
A custom reinforcement learning environment for OpenAI Gym & PettingZoo that implements various Stag Hunt-like social dilemma games.
Repo for reproduction of sequential social dilemmas
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
Stochastic Q-learning for Large Discrete Action Spaces
Simplifying reinforcement learning for complex game environments
An extremely fast Python linter and code formatter, written in Rust.
Benchmarking the Spectrum of Agent Capabilities
The official Python library for Counting Reward Machines.
GameStream client for PCs (Windows, Mac, Linux, and Steam Link)
Self-hosted game stream host for Moonlight.
View your Obsidian notes as interactive recipe cards while you cook.
Advanced player for set-top boxes and tvs running Android OS
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
A suite of test scenarios for multi-agent reinforcement learning.
Implementation of all RL algorithms in a simpler way
A computer algebra system written in pure Python
Extended, multi-agent and multi-objective (MaMoRL / MoMaRL) environments based on DeepMind's AI Safety Gridworlds. This is a suite of reinforcement learning environments illustrating various safety…
This action automatically approves and merges dependabot PRs
Take full control over the order and sorting of folders and notes in File Explorer in Obsidian
A non-saturating, open-ended environment for evaluating LLMs in Factorio
Chrome extension that sorts openrent.co.uk properties in descending order, by recently updated.
Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools.
Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.