2013 · 17 citations · 16 references
EngineeringComputer ScienceRobotics EngineeringRobot LearningRoboticsSafety EngineeringCollision AvoidanceObstacle AvoidancePolicy LearningReinforcement LearningRobot SafetySafe Robot LearningAutomated Model CheckingCollision Avoidance LearningCollision ProbabilityProbabilistic Model CheckingReinforcement Learning For RoboticsSafe LearningStochastic Policy LearningUnsafe Behavior Analysis
Given a stochastic policy learned by reinforcement, we wish to ensure that it can be deployed on a robot with demonstrably low probability of unsafe behavior. Our case study is about learning to reach target objects positioned close to obstacles, and ensuring a reasonably low collision probability. Learning is carried out in a simulator to avoid physical damage in the trial-and-error phase. Once a policy is learned, we analyze it with probabilistic model checking tools to identify and correct potential unsafe behaviors. The whole process is automated and, in principle, it can be integrated step-by-step with routine task-learning. As our results demonstrate, automated fixing of policies is both feasible and highly effective in bounding the probability of unsafe behaviors.
16
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations
On-line Q-learning Using Connectionist Systems
G. A. Rummery · 1994 · 1.5K citations
Computing, Educational Technology, Artificial Intelligence +7
Risk-Sensitive Reinforcement Learning
Oliver Mihatsch, Ralph Neuneier · Machine Learning · 2002 · 262 citations · Full text