More Like this

1. Exploring Induced Pedagogical Strategies Through a Markov Decision Process Framework: Lessons Learned

   Shitian Shen, Behrooz Mostafavi ( December 2018 , Journal of educational data mining)

   An important goal in the design and development of Intelligent Tutoring Systems (ITSs) is to have a system that adaptively reacts to students’ behavior in the short term and effectively improves their learning performance in the long term. Inducing effective pedagogical strategies that accomplish this goal is an essential challenge. To address this challenge, we explore three aspects of a Markov Decision Process (MDP) framework through four experiments. The three aspects are: 1) reward function, detecting the impact of immediate and delayed reward on effectiveness of the policies; 2) state representation, exploring ECR-based, correlation-based, and ensemble feature selection approaches for representing the MDP state space; and 3) policy execution, investigating the effectiveness of stochastic and deterministic policy executions on learning. The most important result of this work is that there exists an aptitude-treatment interaction (ATI) effect in our experiments: the policies have significantly different impacts on the particular types of students as opposed to the entire population. We refer the students who are sensitive to the policies as the Responsive group. All our following results are based on the Responsive group. First, we find that an immediate reward can facilitate a more effective induced policy than a delayed reward. Second, The MDP policies induced based on low correlation-based and ensemble feature selection approaches are more effective than a Random yet reasonable policy. Third, no significant improvement was found using stochastic policy execution due to a ceiling effect. 

   more » « less
2. Exploring Induced Pedagogical Strategies Through a Markov Decision Process Framework: Lessons Learned

   Shen, S. ; Mostafavi, B. ; Barnes, T. ; Chi, M. ( January 2018 , Journal of educational data mining)

   null (Ed.)

   An important goal in the design and development of Intelligent Tutoring Systems (ITSs) is to have a system that adaptively reacts to students’ behavior in the short term and effectively improves their learning performance in the long term. Inducing effective pedagogical strategies that accomplish this goal is an essential challenge. To address this challenge, we explore three aspects of a Markov Decision Process (MDP) framework through four experiments. The three aspects are: 1) reward function, detecting the impact of immediate and delayed reward on effectiveness of the policies; 2) state representation, exploring ECR-based, correlation-based, and ensemble feature selection approaches for representing the MDP state space; and 3) policy execution, investigating the effectiveness of stochastic and deterministic policy executions on learning. The most important result of this work is that there exists an aptitude-treatment interaction (ATI) effect in our experiments: the policies have significantly different impacts on the particular types of students as opposed to the entire population. We refer the students who are sensitive to the policies as the Responsive group. All our following results are based on the Responsive group. First, we find that an immediate reward can facilitate a more effective induced policy than a delayed reward. Second, The MDP policies induced based on low correlation-based and ensemble feature selection approaches are more effective than a Random yet reasonable policy. Third, no significant improvement was found using stochastic policy execution due to a ceiling effect. 

   more » « less
3. Unobserved Is Not Equal to Non-existent: Using Gaussian Processes to Infer Immediate Rewards Across Contexts.

   Hamoon Azizsoltani, Yeo Jin ( January 2019 , In Proceedings of the 28th International Joint Conference on Artificial Intelligence)

   Learning optimal policies in real-world domains with delayed rewards is a major challenge in Reinforcement Learning. We address the credit assignment problem by proposing a Gaussian Process (GP)-based immediate reward approximation algorithm and evaluate its effectiveness in 4 contexts where rewards can be delayed for long trajectories. In one GridWorld game and 8 Atari games, where immediate rewards are available, our results showed that on 7 out 9 games, the proposed GP inferred reward policy performed at least as well as the immediate reward policy and significantly outperformed the corresponding delayed reward policy. In e-learning and healthcare applications, we combined GP-inferred immediate rewards with offline Deep Q-Network (DQN) policy induction and showed that the GP-inferred reward policies outperformed the policies induced using delayed rewards in both real-world contexts. 

   more » « less
4. Empirically Evaluating the Effectiveness of POMDP vs. MDP Towards the Pedagogical Strategies Induction.

   Shen S., Mostafavi B. ( January 2018 , In: Penstein Rosé C. et al. (eds) Artificial Intelligence in Education. AIED 2018. Lecture Notes in Computer Science, vol 10948. Springer, Cham.)

   The effectiveness of Intelligent Tutoring Systems (ITSs) often depends upon their pedagogical strategies, the policies used to decide what action to take next in the face of alternatives. We induce policies based on two general Reinforcement Learning (RL) frameworks: POMDP &. MDP, given the limited feature space. We conduct an empirical study where the RL-induced policies are compared against a random yet reasonable policy. Results show that when the contents are controlled to be equal, the MDP-based policy can improve students’ learning significantly more than the random baseline while the POMDP-based policy cannot outperform the later. The possible reason is that the features selected for the MDP framework may not be the optimal feature space for POMDP. 

   more » « less
5. “Improving Learning & Reducing Time: A Constrained Action-Based Reinforcement Learning Approach.”

   Shen, S. ( January 2018 , In Proceedings of 26th ACM International Conference on User Modeling, Adaptation, and Personalization Conference (ACM UMAP-2018))

   Constrained action-based decision-making is one of the most challenging decision-making problems. It refers to a scenario where an agent takes action in an environment not only to maximize the expected cumulative reward but where it is subject to certain actionbased constraints; for example, an upper limit on the total number of certain actions being carried out. In this work, we construct a general data-driven framework called Constrained Action-based Partially Observable Markov Decision Process (CAPOMDP) to induce effective pedagogical policies. Specifically, we induce two types of policies: CAPOMDP-LG using learning gain as reward with the goal of improving students’ learning performance, and CAPOMDP-Time using time as reward for reducing students’ time on task. The effectiveness ofCAPOMDP-LG is compared against a random yet reasonable policy and the effectiveness of CAPOMDP-Time is compared against both a Deep Reinforcement Learning induced policy and a random policy. Empirical results show that there is an Aptitude Treatment Interaction effect: students are split into High vs. Low based on their incoming competence; while no significant difference is found among the High incoming competence groups, for the Low groups, students following CAPOMDP-Time indeed spent significantly less time than those using the two baseline policies and students following CAPOMDP-LG significantly outperform their peers on both learning gain and learning efficiency. 

   more » « less