Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning

01/13/2023
by   Taylor W. Killian, et al.
0

In safety-critical decision-making scenarios being able to identify worst-case outcomes, or dead-ends is crucial in order to develop safe and reliable policies in practice. These situations are typically rife with uncertainty due to unknown or stochastic characteristics of the environment as well as limited offline training data. As a result, the value of a decision at any time point should be based on the distribution of its anticipated effects. We propose a framework to identify worst-case decision points, by explicitly estimating distributions of the expected return of a decision. These estimates enable earlier indication of dead-ends in a manner that is tunable based on the risk tolerance of the designed task. We demonstrate the utility of Distributional Dead-end Discovery (DistDeD) in a toy domain as well as when assessing the risk of severely ill patients in the intensive care unit reaching a point where death is unavoidable. We find that DistDeD significantly improves over prior discovery approaches, providing indications of the risk 10 hours earlier on average as well as increasing detection by 20

READ FULL TEXT

page 7

page 8

research
11/30/2022

One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning

Offline reinforcement learning (RL) is suitable for safety-critical doma...
research
11/09/2019

Worst Cases Policy Gradients

Recent advances in deep reinforcement learning have demonstrated the cap...
research
12/30/2022

Risk-Sensitive Policy with Distributional Reinforcement Learning

Classical reinforcement learning (RL) techniques are generally concerned...
research
09/16/2020

Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation

Existing neural network-based autonomous systems are shown to be vulnera...
research
11/12/2021

Two steps to risk sensitivity

Distributional reinforcement learning (RL) – in which agents learn about...
research
06/11/2021

Automatic Risk Adaptation in Distributional Reinforcement Learning

The use of Reinforcement Learning (RL) agents in practical applications ...
research
11/28/2017

Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methods

The literature on Inverse Reinforcement Learning (IRL) typically assumes...

Please sign up or login with your details

Forgot password? Click here to reset