skip to main content


Title: Is Reinforcement Learning the Choice of Human Learners?: A Case Study of Taxi Drivers
Learning to make optimal decisions is a common yet complicated task. While computer agents can learn to make decisions by running reinforcement learning (RL), it remains unclear how human beings learn. In this paper, we perform the first data-driven case study on taxi drivers to validate whether humans mimic RL to learn. We categorize drivers into three groups based on their performance trends and analyze the correlations between human drivers and agents trained using RL. We discover that drivers that become more efficient at earning over time exhibit similar learning patterns to those of agents, whereas drivers that become less efficient tend to do the opposite. Our study (1) provides evidence that some human drivers do adapt RL when learning, (2) enhances the deep understanding of taxi drivers' learning strategies, (3) offers a guideline for taxi drivers to improve their earnings, and (4) develops a generic analytical framework to study and validate human learning strategies.  more » « less
Award ID(s):
1942680 1952085 1831140
NSF-PAR ID:
10225178
Author(s) / Creator(s):
; ; ; ; ; ; ;
Date Published:
Journal Name:
Proceedings of the 28th International Conference on Advances in Geographic Information Systems
Page Range / eLocation ID:
357 to 366
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. To make daily decisions, human agents devise their own "strategies" governing their mobility dynamics (e.g., taxi drivers have preferred working regions and times, and urban commuters have preferred routes and transit modes). Recent research such as generative adversarial imitation learning (GAIL) demonstrates successes in learning human decision-making strategies from their behavior data using deep neural networks (DNNs), which can accurately mimic how humans behave in various scenarios, e.g., playing video games, etc. However, such DNN-based models are "black box" models in nature, making it hard to explain what knowledge the models have learned from human, and how the models make such decisions, which was not addressed in the literature of imitation learning. This paper addresses this research gap by proposing xGAIL, the first explainable generative adversarial imitation learning framework. The proposed xGAIL framework consists of two novel components, including Spatial Activation Maximization (SpatialAM) and Spatial Randomized Input Sampling Explanation (SpatialRISE), to extract both global and local knowledge from a well-trained GAIL model that explains how a human agent makes decisions. Especially, we take taxi drivers' passenger-seeking strategy as an example to validate the effectiveness of the proposed xGAIL framework. Our analysis on a large-scale real-world taxi trajectory data shows promising results from two aspects: i) global explainable knowledge of what nearby traffic condition impels a taxi driver to choose a particular direction to find the next passenger, and ii) local explainable knowledge of what key (sometimes hidden) factors a taxi driver considers when making a particular decision. 
    more » « less
  2. null (Ed.)
    Smart passenger-seeking strategies employed by taxi drivers contribute not only to drivers’ incomes, but also higher quality of service passengers received. Therefore, understanding taxi drivers’ behaviors and learning the good passenger-seeking strategies are crucial to boost taxi drivers’ well-being and public transportation quality of service. However, we observe that drivers’ preferences of choosing which area to find the next passenger are diverse and dynamic across locations and drivers. It is hard to learn the location-dependent preferences given the partial data (i.e., an individual driver's trajectory may not cover all locations). In this paper, we make the first attempt to develop conditional generative adversarial imitation learning (cGAIL) model, as a unifying collective inverse reinforcement learning framework that learns the driver's decision-making preferences and policies by transferring knowledge across taxi driver agents and across locations. Our evaluation results on three months of taxi GPS trajectory data in Shenzhen, China, demonstrate that the driver's preferences and policies learned from cGAIL are on average 34.7% more accurate than those learned from other state-of-the-art baseline approaches. 
    more » « less
  3. null (Ed.)
    Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present an off-policy, interactive RL algorithm that capitalizes on the strengths of both feedback and off-policy learning. Specifically, we learn a reward model by actively querying a teacher’s preferences between two clips of behavior and use it to train an agent. To enable off-policy learning, we relabel all the agent’s past experience when its reward model changes. We additionally show that pre-training our agents with unsupervised exploration substantially increases the mileage of its queries. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods, including a variety of locomotion and robotic manipulation skills. We also show that our method is able to utilize real-time human feedback to effectively prevent reward exploitation and learn new behaviors that are difficult to specify with standard reward functions. 
    more » « less
  4. null (Ed.)
    Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present an off-policy, interactive RL algorithm that capitalizes on the strengths of both feedback and off-policy learning. Specifically, we learn a reward model by actively querying a teacher’s preferences between two clips of behavior and use it to train an agent. To enable off-policy learning, we relabel all the agent’s past experience when its reward model changes. We additionally show that pre-training our agents with unsupervised exploration substantially increases the mileage of its queries. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods, including a variety of locomotion and robotic manipulation skills. We also show that our method is able to utilize real-time human feedback to effectively prevent reward exploitation and learn new behaviors that are difficult to specify with standard reward functions. 
    more » « less
  5. Mobile wireless networks present several challenges for any learning system, due to uncertain and variable device movement, a decentralized network architecture, and constraints on network resources. In this work, we use deep reinforcement learning (DRL) to learn a scalable and generalizable forwarding strategy for such networks. We make the following contributions: i) we use hierarchical RL to design DRL packet agents rather than device agents, to capture the packet forwarding decisions that are made over time and improve training efficiency; ii) we use relational features to ensure generalizability of the learned forwarding strategy to a wide range of network dynamics and enable offline training; and iii) we incorporate both forwarding goals and network resource considerations into packet decision-making by designing a weighted DRL reward function. Our results show that our DRL agent often achieves a similar delay per packet delivered as the optimal forwarding strategy and outperforms all other strategies including state-of-the-art strategies, even on scenarios on which the DRL agent was not trained. 
    more » « less