• Corpus ID: 189762098

Modeling and Interpreting Real-world Human Risk Decision Making with Inverse Reinforcement Learning

  title={Modeling and Interpreting Real-world Human Risk Decision Making with Inverse Reinforcement Learning},
  author={Quanying Liu and Haiyan Wu and Anqi Liu},
We model human decision-making behaviors in a risk-taking task using inverse reinforcement learning (IRL) for the purposes of understanding real human decision making under risk. To the best of our knowledge, this is the first work applying IRL to reveal the implicit reward function in human risk-taking decision making and to interpret risk-prone and risk-averse decision-making policies. We hypothesize that the state history (e.g. rewards and decisions in previous trials) are related to the… 

Figures and Tables from this paper

Analyzing Sensor-Based Individual and Population Behavior Patterns via Inverse Reinforcement Learning

A novel algorithm is introduced—Resident Relative Entropy-Inverse Reinforcement Learning (RRE-IRL)—to perform an analysis of a single smart home resident or a group of residents, using inverse reinforcement learning, and it is observed that the behavioral routine preferences changed over time.

Examining Polarized COVID-19 Twitter Discussion Using Inverse Reinforcement Learning

This work model users’ behavior on Twitter in discussion of the COVID-19 outbreak using inverse reinforcement learning to better understand the underlying forces that drive the observed pattern of polarization, and demonstrates the aptitude of inverse reinforcementLearning in helping understand user behavior on social media.

Augmented Human Intelligence for Decision Making in Maintenance Risk Taking Tasks using Reinforcement Learning

A new RL-based model framework is proposed that can categorically infer the user-defined human risk attitude, and the trained RL agent demonstrates its rational decision-making prowess by outperforming the majority of human participants.



Adaptive learning and risk taking.

A formal theory of how adaptive sampling influences risk taking is developed, showing that a risk-neutral decision maker may learn to prefer a sure thing to an uncertain alternative with identical expected value and a symmetric distribution, even if the decision maker follows an optimal policy of learning.

Learning to be risk averse?

  • R. Marks
  • Economics
    2014 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr)
  • 2014
The Genetic Algorithm is used to search for the best (highest performing) risk profile of agents who successively choose among risky prospects and finds that agents with a CARA utility function learn to possess risk-neutral risk profiles.

Modeling behavior in a clinically diagnostic sequential risk-taking task.

This article models the cognitive processes underlying learning and sequential choice in a risk-taking task for the purposes of understanding how they occur in this moderately complex environment and

Apprenticeship learning via inverse reinforcement learning

This work thinks of the expert as trying to maximize a reward function that is expressible as a linear combination of known features, and gives an algorithm for learning the task demonstrated by the expert, based on using "inverse reinforcement learning" to try to recover the unknown reward function.

Neuroelectric Signatures of Reward Learning and Decision-Making in the Human Nucleus Accumbens

The high spatial and temporal resolution of these recordings provides novel insights into the timing of activity in the human nucleus accumbens, its functions during reward-guided learning and decision-making, and its interactions with medial frontal cortex.

Maximum Entropy Inverse Reinforcement Learning

A probabilistic approach based on the principle of maximum entropy that provides a well-defined, globally normalized distribution over decision sequences, while providing the same performance guarantees as existing methods is developed.

A survey of inverse reinforcement learning techniques

The original IRL algorithms and its close variants, as well as their recent advances are reviewed and compared.

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

This paper proposes a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting and demonstrates that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.

Socially compliant mobile robot navigation via inverse reinforcement learning

An extensive set of experiments suggests that the technique outperforms state-of-the-art methods to model the behavior of pedestrians, which also makes it applicable to fields such as behavioral science or computer graphics.