Timezone: »
When a robot observes another agent unexpectedly modifying their behavior, inferring the most likely cause is a valuable tool for maintaining safety and reacting appropriately. In this work, we present a novel method for inferring constraints that works on continuous, possibly sub-optimal demonstrations. We first learn a representation of the continuous-state maximum entropy trajectory distribution using deep reinforcement learning. We then use Monte Carlo sampling from this distribution to generate expected constraint violation probabilities and perform constraint inference. When the agent's dynamics and objective function are known in advance, this process can be performed offline, allowing for real-time constraint inference at the moment demonstrations are observed. We demonstrate our approach on two continuous systems, including a human driving a model car.
Author Information
Kaylene Stocking (UC Berkeley)
David McPherson (University of California, Berkeley)
Robert Matthew (University of California, San Francisco)
Claire Tomlin (UC Berkeley)
More from the Same Authors
-
2021 : Safely Learning Behaviors of Other Agents »
Claire Tomlin -
2021 : Safe RL Panel Discussion »
Animesh Garg · Marek Petrik · Shie Mannor · Claire Tomlin · Ugo Rosolia · Dylan Hadfield-Menell -
2017 Poster: Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach »
Roel Dobbe · David Fridovich-Keil · Claire Tomlin -
2017 Poster: Countering Feedback Delays in Multi-Agent Learning »
Zhengyuan Zhou · Panayotis Mertikopoulos · Nicholas Bambos · Peter W Glynn · Claire Tomlin -
2016 Poster: Minimizing Regret on Reflexive Banach Spaces and Nash Equilibria in Continuous Zero-Sum Games »
Maximilian Balandat · Walid Krichene · Claire Tomlin · Alexandre Bayen