Probabilistically safe policy transfer
By David Held, Zoe McCarthy, Michael Zhang, Fred Shentu, Pieter Abbeel. 2017
22 citations recorded by the source corpus.
Although learning-based methods have great potential for robotics, one concern is that a robot that updates its parameters might cause large amounts of damage before it learns the optimal policy. We formalize the idea of safe learning in a probabilistic sense by defining an optimization problem: we desire to maximize the expected return while keeping the expected damage below a given safety limit. We study this optimization for the case of a robot manipulator with safety-based torque limits. We would like to ensure that the damage constraint is maintained at every step of the optimization and not just at convergence. To achieve this aim, we introduce a novel method which predicts how modifying the torque limit, as well as how updating the policy parameters, might affect the robot's safety. We show through a number of experiments that our approach allows the robot to improve its performance while ensuring that the expected damage constraint is not violated during the learning process.
Subfields: Artificial Intelligence, Software, Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Pieter Abbeel
- Chelsea Finn
- Ruslan Salakhutdinov
- Yoshua Bengio
- Trevor Darrell
- Mohit Bansal
- Percy Liang
In Software
In Reinforcement Learning
- Sergey Levine
- Pieter Abbeel
- Chelsea Finn
- Lerrel Pinto
- Marcin Andrychowicz
- David Held
- Wojciech Zaremba
- Ofir Nachum
Citations in the corpus
- Constrained Policy Optimization (2017, background): “Held et al. (2017) study the problem for robotic manipulation, but the assumptions they make restrict the applicability of their methods.”
- Asymmetric Actor Critic for Image-Based Robot Learning (2017, background): “A recent approach to circumvent these challenges is to train on a simulated version of the robot and then transfer to the real robot [5]–[12].”
- Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning (2018, background): “Our goal is orthogonal to providing safety guarantees [15, 22, 43].”