no code implementations • 15 Jun 2021 • Abbas Abdolmaleki, Sandy H. Huang, Giulia Vezzani, Bobak Shahriari, Jost Tobias Springenberg, Shruti Mishra, Dhruva TB, Arunkumar Byravan, Konstantinos Bousmalis, Andras Gyorgy, Csaba Szepesvari, Raia Hadsell, Nicolas Heess, Martin Riedmiller
We highlight its strengths on standard MO benchmark problems and consider case studies in which we recast offline RL and learning from experts as MO problems.
1 code implementation • 15 May 2020 • Abbas Abdolmaleki, Sandy H. Huang, Leonard Hasenclever, Michael Neunert, H. Francis Song, Martina Zambelli, Murilo F. Martins, Nicolas Heess, Raia Hadsell, Martin Riedmiller
Many real-world problems require trading off multiple competing objectives.
People frequently face challenging decision-making problems in which outcomes are uncertain or unknown.
In order to effectively interact with or supervise a robot, humans need to have an accurate mental model of its capabilities and how it acts.
We show that certain approximate-inference models lead to the robot generating example behaviors that better enable users to anticipate what it will do in novel situations.