Oral
Inverse Reward Design
Dylan Hadfield-Menell · Smitha Milli · Pieter Abbeel · Stuart J Russell · Anca Dragan

Wed Dec 6th 04:50 -- 05:05 PM @ Hall A

Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When designing the reward, we might think of some specific scenarios (driving on clean roads), and make sure that the reward will lead to the right behavior in \emph{those} scenarios. Inevitably, agents encounter \emph{new} scenarios (snowy roads), and optimizing the reward can lead to undesired behavior (driving too fast). Our insight in this work is that reward functions are merely \emph{observations} about what the designer \emph{actually} wants, and that they should be interpreted in the context in which they were designed. We introduce \emph{Inverse Reward Design} (IRD) as the problem of inferring the true reward based on the designed reward and the training MDP. We introduce approximate methods for solving IRD problems, and use their solution to plan risk-averse behavior in test MDPs. Empirical results suggest that this approach takes a step towards alleviating negative side effects and preventing reward hacking.

Author Information

Dylan Hadfield-Menell (UC Berkeley)
Smitha Milli (UC Berkeley)
Pieter Abbeel (UC Berkeley | Gradescope | Covariant)

Pieter Abbeel is Professor and Director of the Robot Learning Lab at UC Berkeley [2008- ], Co-Director of the Berkeley AI Research (BAIR) Lab, Co-Founder of covariant.ai [2017- ], Co-Founder of Gradescope [2014- ], Advisor to OpenAI, Founding Faculty Partner AI@TheHouse venture fund, Advisor to many AI/Robotics start-ups. He works in machine learning and robotics. In particular his research focuses on making robots learn from people (apprenticeship learning), how to make robots learn through their own trial and error (reinforcement learning), and how to speed up skill acquisition through learning-to-learn (meta-learning). His robots have learned advanced helicopter aerobatics, knot-tying, basic assembly, organizing laundry, locomotion, and vision-based robotic manipulation. He has won numerous awards, including best paper awards at ICML, NIPS and ICRA, early career awards from NSF, Darpa, ONR, AFOSR, Sloan, TR35, IEEE, and the Presidential Early Career Award for Scientists and Engineers (PECASE). Pieter's work is frequently featured in the popular press, including New York Times, BBC, Bloomberg, Wall Street Journal, Wired, Forbes, Tech Review, NPR.

Stuart J Russell (UC Berkeley)
Anca Dragan (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors