skip to main content


Title: Empirically Evaluating the Effectiveness of POMDP vs. MDP Towards the Pedagogical Strategies Induction.
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
Award ID(s):
1726550
NSF-PAR ID:
10065910
Author(s) / Creator(s):
Date Published:
Journal Name:
In: Penstein Rosé C. et al. (eds) Artificial Intelligence in Education. AIED 2018. Lecture Notes in Computer Science, vol 10948. Springer, Cham.
Page Range / eLocation ID:
327-331
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. 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. 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. 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
  4. We study model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov decision process (MDP), which is more appropriate for applications that involve continuing operations not divided into episodes. In contrast to episodic/discounted MDPs, theoretical understanding of model-free RL algorithms is relatively inadequate for the average-reward setting. In this paper, we consider both the online setting and the setting with access to a simulator. We develop computationally efficient model-free algorithms that achieve sharper guarantees on regret/sample complexity compared with existing results. In the online setting, we design an algorithm, UCB-AVG, based on an optimistic variant of variance-reduced Q-learning. We show that UCB-AVG achieves a regret bound $\widetilde{O}(S^5A^2sp(h^*)\sqrt{T})$ after $T$ steps, where $S\times A$ is the size of state-action space, and $sp(h^*)$ the span of the optimal bias function. Our result provides the first computationally efficient model-free algorithm that achieves the optimal dependence in $T$ (up to log factors) for weakly communicating MDPs, which is necessary for low regret. In contrast, prior results either are suboptimal in $T$ or require strong assumptions of ergodicity or uniformly mixing of MDPs. In the simulator setting, we adapt the idea of UCB-AVG to develop a model-free algorithm that finds an $\epsilon$-optimal policy with sample complexity $\widetilde{O}(SAsp^2(h^*)\epsilon^{-2} + S^2Asp(h^*)\epsilon^{-1}).$ This sample complexity is near-optimal for weakly communicating MDPs, in view of the minimax lower bound $\Omega(SAsp(^*)\epsilon^{-2})$. Existing work mainly focuses on ergodic MDPs and the results typically depend on $t_{mix},$ the worst-case mixing time induced by a policy. We remark that the diameter $D$ and mixing time $t_{mix}$ are both lower bounded by $sp(h^*)$, and $t_{mix}$ can be arbitrarily large for certain MDPs. On the technical side, our approach integrates two key ideas: learning an $\gamma$-discounted MDP as an approximation, and leveraging reference-advantage decomposition for variance in optimistic Q-learning. As recognized in prior work, a naive approximation by discounted MDPs results in suboptimal guarantees. A distinguishing feature of our method is maintaining estimates of value-difference between state pairs to provide a sharper bound on the variance of reference advantage. We also crucially use a careful choice of the discounted factor $\gamma$ to balance approximation error due to discounting and the statistical learning error, and we are able to maintain a good-quality reference value function with $O(SA)$ space complexity. 
    more » « less
  5. This paper presents a framework to learn the reward function underlying high-level sequential tasks from demonstrations. The purpose of reward learning, in the context of learning from demonstration (LfD), is to generate policies that mimic the demonstrator’s policies, thereby enabling imitation learning. We focus on a human-robot interaction(HRI) domain where the goal is to learn and model structured interactions between a human and a robot. Such interactions can be modeled as a partially observable Markov decision process (POMDP) where the partial observability is caused by uncertainties associated with the ways humans respond to different stimuli. The key challenge in finding a good policy in such a POMDP is determining the reward function that was observed by the demonstrator. Existing inverse reinforcement learning(IRL) methods for POMDPs are computationally very expensive and the problem is not well understood. In comparison, IRL algorithms for Markov decision process (MDP) are well defined and computationally efficient. We propose an approach of reward function learning for high-level sequential tasks from human demonstrations where the core idea is to reduce the underlying POMDP to an MDP and apply any efficient MDP-IRL algorithm. Our extensive experiments suggest that the reward function learned this way generates POMDP policies that mimic the policies of the demonstrator well. 
    more » « less