Potential-based multiobjective reinforcement learning approaches to low-impact agents for AI safety

Peter Vamplew 0001, Cameron Foale, Richard Dazeley, Adam Bignold. Potential-based multiobjective reinforcement learning approaches to low-impact agents for AI safety. Eng. Appl. of AI, 100:104186, 2021. [doi]

Authors

Peter Vamplew 0001

This author has not been identified. Look up 'Peter Vamplew 0001' in Google

Cameron Foale

This author has not been identified. Look up 'Cameron Foale' in Google

Richard Dazeley

This author has not been identified. Look up 'Richard Dazeley' in Google

Adam Bignold

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