Lists (3)
Sort Name ascending (A-Z)
Starred repositories
WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
Motion films that never cut to the next slide: every beat grows out of the one before, one continuous camera, continuity measured by an oracle. Product launch films and feature demos, made with a c…
Easily implement custom Gymnasium environments for real-time applications
Reverse engineering the classic GTA Vice City game
TextStarCraft2,a pure language env which support llms play starcraft2
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement …
A simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games
A fork of gym-retro with additional games, emulators and supported platforms
DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation
Decision Index: reproduce the Jev decision-model benchmark suite locally or as one HF Job
Gym-style environment for Warcraft III Legacy: stepping, observations and commands through an injected DLL
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
A curated list of reinforcement learning environments — from classic control to the LLM-agent training environments powering frontier models.
Poke-env: Python Interface for Pokemon Showdown Bots
High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogeneous engines and extreme memory efficiency for GRPO, PPO, etc.
Evaluate and improve models and agents using environments
📄Score Centering Stabilizes Off-policy Reinforcement Learning
A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.
Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.
The open, local take on Jev: typed decisions from an LLM, without generating a single token
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own