8000 jacklanda (Michael Liu) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View jacklanda's full-sized avatar
🌻
🌻

Block or report jacklanda

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Starred repositories

Showing results

WebHarbor: Docking Real Websites for Evolving GUI Agent Environments

Python 77 42 Updated Nov 3, 2026

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…

Python 4,164 291 Updated Nov 5, 2026

"Age of Empires II" Learning Environment

Python 92 13 Updated Jul 12, 2021

Easily implement custom Gymnasium environments for real-time applications

Python 107 6 Updated May 26, 2025

Reverse engineering the classic GTA Vice City game

C++ 489 147 Updated Oct 2, 2026
TypeScript 193 14 Updated Sep 27, 2026

General System One

Python 18 4 Updated Nov 16, 2026

TextStarCraft2,a pure language env which support llms play starcraft2

Python 391 28 Updated Apr 25, 2025

A Gym for Agentic LLMs

Python 518 33 Updated Jan 21, 2026

The Stratagus strategy game engine

C++ 748 143 Updated Nov 16, 2026

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 …

C# 19,876 4,520 Updated Oct 30, 2026

A simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games

C++ 2,465 485 Updated Nov 15, 2026

A fork of gym-retro with additional games, emulators and supported platforms

C++ 1,100 88 Updated Nov 12, 2026

DeSmuME is a Nintendo DS emulator

C++ 3,693 657 Updated Nov 13, 2026

DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation

Python 369 29 Updated Jun 11, 2024

Decision Index: reproduce the Jev decision-model benchmark suite locally or as one HF Job

Python 98 170 Updated Oct 20, 2026

Gym-style environment for Warcraft III Legacy: stepping, observations and commands through an injected DLL

C 30 2 Updated Nov 1, 2026

StarCraft II Learning Environment

Python 8,337 1,163 Updated Jul 23, 2024

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Python 12,827 1,541 Updated Nov 12, 2026

A curated list of reinforcement learning environments — from classic control to the LLM-agent training environments powering frontier models.

7 Updated Jun 23, 2026

Poke-env: Python Interface for Pokemon Showdown Bots

Python 542 149 Updated Nov 15, 2026

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.

Python 461 138 Updated Nov 16, 2026

Evaluate and improve models and agents using environments

Python 1,335 476 Updated Nov 16, 2026

📄Score Centering Stabilizes Off-policy Reinforcement Learning

Python 239 17 Updated Oct 27, 2026

A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.

Python 1,054 55 Updated Oct 20, 2026

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.

Python 493 55 Updated Oct 16, 2026

The open, local take on Jev: typed decisions from an LLM, without generating a single token

Python 964 65 Updated Sep 25, 2026

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)

Python 1,614 180 Updated Oct 21, 2026

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

Python 10,006 685 Updated Nov 15, 2026
Next
0