Student-Tutor Mixed-Initiative Decision-Making Supported by Deep Reinforcement Learning

Ju, Song Hyun; Yang, Xi; Barnes, Tiffany; Chi, Min

doi:10.1007/978-3-031-11644-5_36

Cited by 1 publication

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies found that immediate rewards can help with policy learning in terms of convergence and rewards in offline RL (Ausin et al 2021;Azizsoltani et al 2019;Fahid et al 2022). Others investigated students' agency in pedagogical decisions using offline RL (Ju et al 2022). Some studies have investigated offline RL-based pedagogical planning in narrative-centered learning environments.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Online Reinforcement Learning-Based Pedagogical Planning for Narrative-Centered Learning Environments

Fahid,

Rowe,

Kim

et al. 2024

AAAI

View full text Add to dashboard Cite

Pedagogical planners can provide adaptive support to students in narrative-centered learning environments by dynamically scaffolding student learning and tailoring problem scenarios. Reinforcement learning (RL) is frequently used for pedagogical planning in narrative-centered learning environments. However, RL-based pedagogical planning raises significant challenges due to the scarcity of data for training RL policies. Most prior work has relied on limited-size datasets and offline RL techniques for policy learning. Unfortunately, offline RL techniques do not support on-demand exploration and evaluation, which can adversely impact the quality of induced policies. To address the limitation of data scarcity and offline RL, we propose INSIGHT, an online RL framework for training data-driven pedagogical policies that optimize student learning in narrative-centered learning environments. The INSIGHT framework consists of three components: a narrative-centered learning environment simulator, a simulated student agent, and an RL-based pedagogical planner agent, which uses a reward metric that is associated with effective student learning processes. The framework enables the generation of synthetic data for on-demand exploration and evaluation of RL-based pedagogical planning. We have implemented INSIGHT with OpenAI Gym for a narrative-centered learning environment testbed with rule-based simulated student agents and a deep Q-learning-based pedagogical planner. Our results show that online deep RL algorithms can induce near-optimal pedagogical policies in the INSIGHT framework, while offline deep RL algorithms only find suboptimal policies even with large amounts of data.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Although this approach has shown significant promise (Ju et al 2022;Zhou et al 2022), offline RL has limited capabilities in terms of learning and evaluating policies. With relatively small datasets and no exploration, offline RL can yield suboptimal policies (Prudencio et al 2023).…”

Section: Introductionmentioning

confidence: 99%