Extended, multi-agent, and multi-objective (MaMoRL / MoMaRL) gridworld environments building framework based on DeepMind's AI Safety Gridworlds. This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. It is made compatible with OpenAI's Gym/Gymnasium and Farama Foundation PettingZoo.
simulation-environment constraint-satisfaction-problem artificial-intelligence multi-agent gym simulation-framework rl multi-objective-optimization gridworld multi-objective ai-safety human-player gridworld-environment reinforcement-learning-environments marl sideeffects multiobjective-learning morl pettingzoo pluralism
-
Updated
Jun 21, 2026 - Python