Inverse Risk-Sensitive Reinforcement Learning
This work addresses the challenge of modeling human decision-making under risk for applications like ride-sharing, though it appears incremental as it adapts existing inverse reinforcement learning methods to incorporate risk-sensitivity.
The paper tackles the problem of inverse reinforcement learning for risk-sensitive agents in Markov decision processes, proposing a gradient-based algorithm that minimizes a loss function on observed behavior, and demonstrates its performance on a Grid World example and a ride-sharing decision model using real pricing and travel time data.
We address the problem of inverse reinforcement learning in Markov decision processes where the agent is risk-sensitive. In particular, we model risk-sensitivity in a reinforcement learning framework by making use of models of human decision-making having their origins in behavioral psychology, behavioral economics, and neuroscience. We propose a gradient-based inverse reinforcement learning algorithm that minimizes a loss function defined on the observed behavior. We demonstrate the performance of the proposed technique on two examples, the first of which is the canonical Grid World example and the second of which is a Markov decision process modeling passengers' decisions regarding ride-sharing. In the latter, we use pricing and travel time data from a ride-sharing company to construct the transition probabilities and rewards of the Markov decision process.