Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision makers. One perspective for formalising and addressing such tasks is multi-objective multi-agent reinforcement learning. This broadens reinforcement learning to problems with multiple agents each needing to consider multiple objectives in their learning process.
To support the advancement of the field, we have developed MOMAland, the first collection of standardised environments for multi-objective multi-agent reinforcement learning. MOMAland addresses the need for comprehensive benchmarking in this emerging field, offering over 10 diverse environments that vary in the number of agents, state representations, reward structures, and utility considerations. To provide strong baselines for future research, MOMAland also includes algorithms capable of learning policies in such settings.
MOMAland is an open source Python library that is part of the Farama Foundation, a non-profit organisation that maintains open source RL tools.
