Category

Gaming & Simulation

NPCs, procedural content, balancing.

13 listings

Every Gaming & Simulation listing on ai-supply is a free, open-source AI capability that we scan and grade A–D for security before it appears here — so you can adopt with confidence, not just a star count. This category spans 5 Evals, 4 Skills, 1 Agent, 1 Pipeline, 1 Dataset and 1 MCP server.

Security posture: 6 of 13 scanned rated safe · avg score 90/100.

Gaming & Simulation leaderboard →How we grade security →Security findings →All categories →

Gymnasium — Standard RL Environment API

Farama Foundation's MIT-licensed reinforcement learning toolkit — the standard interface for RL environments including Atari, MuJoCo, CartPole, and 100+ more.

✓ A · 100⟳ 3mo agoshellfs

Stable-Baselines3 — Reliable RL Algorithm Implementations

DLR's MIT-licensed PyTorch implementations of PPO, SAC, TD3, DQN, A2C, and HER — battle-tested RL algorithms for game AI and simulation.

✓ A · 100⟳ 1mo agoshellfs

Unity ML-Agents — Deep RL for Game NPCs

Apache-2.0 toolkit for training intelligent game agents using deep RL and imitation learning directly inside Unity game environments.

! B · 75⟳ 10mo agoshellnetworkfs

PettingZoo — Multi-Agent Reinforcement Learning

Farama Foundation's MIT-licensed multi-agent RL environment library — 50+ cooperative and competitive games for training and evaluating MARL algorithms.

! B · 75⟳ 3mo agoshellfs

OpenSpiel — Game Theory & RL Research Framework

DeepMind's Apache-2.0 framework for game theory and RL research: 70+ games (Chess, Go, Poker, Hex), CFR, MCTS, deep RL, and Nash equilibrium solvers.

✓ A · 100⟳ 11d agosecretsshellnetwork

MiniGrid — Minimalistic Gridworld Environments

Farama Foundation's Apache-2.0 fast gridworld RL environments for goal-conditioned, partially observable, and language-conditioned agent research.

✓ A · 100⟳ 2mo agofs

procgen — Procedural Game Environments for RL

OpenAI's MIT-licensed suite of 16 procedurally-generated 2D game environments for measuring generalization in reinforcement learning agents.

! B · 75⟳ 4y agoguards:1

Google Research Football

Physics-based 11-vs-11 football RL environment for training and benchmarking game-playing agents, from the Google Brain team.

! B · 88⟳ 4y agoguards:1

Gymnasium Robotics — RL Robotics Environments

Farama Foundation's collection of robotics simulation RL environments: FetchReach, ShadowHand, Maze, AdroitHand.

✓ A · 100⟳ 6mo agoPII

PySC2 (StarCraft II Learning Environment)

DeepMind's Python interface to the StarCraft II Learning Environment, exposing the game as an RL testbed for game-agent research.

! B · 88⟳ 4y agoguards:3

Melting Pot — Multi-Agent RL Test Suite

Google DeepMind's suite of 50+ multi-agent social RL scenarios testing cooperation, competition, and generalization.

! B · 88⟳ 1y agoguards:1

Procedurally generated open-world survival benchmark that evaluates a broad range of RL and world-model agent abilities.

✓ A · 100⟳ 2y ago

◇MCP 服务器

Bridges AI assistants with the Unity Editor to manage assets, scenes, scripts, and tests.

! B · 75⟳ 14d agoshellnetworkfs