MOMA-AC: A preference-driven actor-critic framework for continuous multi-objective multi-agent reinforcement learning

Adam Callaghan, Karl Mason, Patrick Mannion. MOMA-AC: A preference-driven actor-critic framework for continuous multi-objective multi-agent reinforcement learning. Neurocomputing, 664:132032, 2026. [doi]

Authors

Adam Callaghan

This author has not been identified. Look up 'Adam Callaghan' in Google

Karl Mason

This author has not been identified. Look up 'Karl Mason' in Google

Patrick Mannion

This author has not been identified. Look up 'Patrick Mannion' in Google