• Home
  • About Us
  • Contact Us
  • Privacy Policy
  • Special Offers
Business Intelligence Info
  • Business Intelligence
    • BI News and Info
    • Big Data
    • Mobile and Cloud
    • Self-Service BI
  • CRM
    • CRM News and Info
    • InfusionSoft
    • Microsoft Dynamics CRM
    • NetSuite
    • OnContact
    • Salesforce
    • Workbooks
  • Data Mining
    • Pentaho
    • Sisense
    • Tableau
    • TIBCO Spotfire
  • Data Warehousing
    • DWH News and Info
    • IBM DB2
    • Microsoft SQL Server
    • Oracle
    • Teradata
  • Predictive Analytics
    • FICO
    • KNIME
    • Mathematica
    • Matlab
    • Minitab
    • RapidMiner
    • Revolution
    • SAP
    • SAS/SPSS
  • Humor

Uber researchers investigate whether AI can behave ethically

June 11, 2020   Big Data

Can AI behave ethically? That’s the intractable question researchers at Uber set out to answer in a preprint paper, which attempts to translate insights from moral philosophy to the field of reinforcement learning — the area of machine learning concerned with how software agents ought to take actions in an environment to maximize their reward.

While reinforcement learning is a powerful technique, it often must be constrained in real-world, unstructured environments so that it doesn’t perform tasks unacceptably poorly. (A robot vacuum shouldn’t break a vase or harm a house cat, for instance.) Reinforcement learning-trained robots in particular have affordances with ethical implications insofar as they might be able to harm or to help others. Realizing this, the Uber team considered the possibility that there’s no single ethical theory (e.g., utilitarianism, deontology, and virtue ethics) an agent should follow, and that agents should instead act with uncertainty as to which theory is appropriate for a given context.

“[M]achine learning might have an important role to play [in this],” the researchers postulate. “Classifiers can be trained to recognize morally relevant events and situations, such as bodily harm or its potential, emotional responses to humans and animals, and violations of laws or … norms.”

The coauthors assume the relevant feature of an ethical theory is its preference for certain actions and their outcomes within an environment. They assign theories a level of credence that represents the degree of belief the agent or the agent’s designer had in the theories, and they use a modified version of a standard framework (a Markov Decision Process) in which an agent can be in any number of states and take an action to reach a different state.

VB Transform 2020 Online – July 15-17. Join leading AI executives: Register for the free livestream.

 Uber researchers investigate whether AI can behave ethically

The researchers suggest ethical theories can be treated according to the principle of Proportional Say, under which the theories have influence proportional only to their credence and not to the particular details of their choice-worthiness in the final decision. They devise several systems based on this that an agent might use to select theories, which they compare across four related grid-world environments designed to tease out the differences between the various systems.

All environments deal with the trolley problem, in which a person — or agent — is forced to decide whether to sacrifice the lives of several people or the life of one. Within the grid-worlds, the trolley normally moves right at each time step. If the agent is standing on a switch tile at the time it reaches a fork in the tracks, the trolley will be redirected down and crash into a bystander, causing harm. Alternatively, the agent can push a large man onto the tracks, harming him but stopping the trolley. (A guard might protect the man, in which case the agent must lie to the guard.) The trolley otherwise continues on its way and crashes into people represented by the variable “X.”

According to the researchers, an agent that attempts to maximize expected choice-worthiness produces inconsistent results between the theories of utilitarianism (which counts all harms) and deontology (which counts only harms caused by the agent). However, this depends on whether the deontological theory is scaled by a factor of 1 or 10; the researchers struggled to reconcile the different units used by utilitarianism and deontology.

On the other hand, an agent that relies on a technique called Nash voting is always likely to choose the theory with the highest credence. That’s because Nash voting disagrees with the notion of stakes sensitivity, in which as “X” increases, utilitarianism’s preference for flipping the switch is taken into greater consideration. Nash voting also fails to compromise — it always ignores the “switch” option, only ever choosing to push the large man or do nothing when faced with the choice of (1) letting the trolley crash into a large number of people, (2) redirecting the trolley onto a different track on which two people are standing, or (3) pushing the man.

As for an agent that aggregates preferences obtained using Q-learning, an algorithm that learns a policy telling an agent what action to take under what circumstances, it suffers from a phenomenon known as the illusion of control. Q-learning implicitly assumes that the action taken by the policy will be whatever maximizes the reward, when in fact the preferred next action might vary across different theories. In the trolley problem, the Q-learning agent often opts to lie to the guard without pushing the man, because the agent mistakenly believes it will be able to push the man in the following step.

The experimental results seem to imply a range of possible algorithms that cover tradeoffs among competing options in decision-making under moral uncertainty. The algorithm that’s most appropriate for a given domain might depend on particularities of the theories and the domain itself, the researchers suspect, which is why they plan to test algorithms for moral uncertainty (and machine ethics in general) in more complex domains.

Beyond this Uber paper, Mobileye, Nvidia, DeepMind, and OpenAI have published work on safety constraints in reinforcement learning techniques. DeepMind recently investigated a method for reward modeling that operates in two phases and is applicable to environments in which agents don’t know where unsafe states might be. For its part, OpenAI released Safety Gym, a suite of tools for developing AI that respects safety constraints while training and compares the safety of algorithms and the extent to which those algorithms avoid mistakes while learning.

Let’s block ads! (Why?)

Big Data – VentureBeat

behave, ethically, Investigate, researchers, Uber, Whether
  • Recent Posts

    • The Great Awakening?
    • Another Success Story: McWane
    • The Dynamics 365 Sales Mobile App Helps Salespeople Stay Productive From Anywhere
    • THEY CAN FIND THE GUY WHO BROKE A WINDOW BUT NOT A MURDERER?
    • TIBCO4Good and She Loves Data Offer Free Data Skills Workshops During a Time of Vulnerability
  • Categories

  • Archives

    • January 2021
    • December 2020
    • November 2020
    • October 2020
    • September 2020
    • August 2020
    • July 2020
    • June 2020
    • May 2020
    • April 2020
    • March 2020
    • February 2020
    • January 2020
    • December 2019
    • November 2019
    • October 2019
    • September 2019
    • August 2019
    • July 2019
    • June 2019
    • May 2019
    • April 2019
    • March 2019
    • February 2019
    • January 2019
    • December 2018
    • November 2018
    • October 2018
    • September 2018
    • August 2018
    • July 2018
    • June 2018
    • May 2018
    • April 2018
    • March 2018
    • February 2018
    • January 2018
    • December 2017
    • November 2017
    • October 2017
    • September 2017
    • August 2017
    • July 2017
    • June 2017
    • May 2017
    • April 2017
    • March 2017
    • February 2017
    • January 2017
    • December 2016
    • November 2016
    • October 2016
    • September 2016
    • August 2016
    • July 2016
    • June 2016
    • May 2016
    • April 2016
    • March 2016
    • February 2016
    • January 2016
    • December 2015
    • November 2015
    • October 2015
    • September 2015
    • August 2015
    • July 2015
    • June 2015
    • May 2015
    • April 2015
    • March 2015
    • February 2015
    • January 2015
    • December 2014
    • November 2014
© 2021 Business Intelligence Info
Power BI Training | G Com Solutions Limited