Interactive teaching mode based on deep reinforcement learning

Jun Shao

Abstract


interactive teaching mode has been widely used in the teaching process of all levels and courses. With the deepening of
interactive teaching, the restrictions on interactive time, interactive scene, interactive means and other aspects are becoming more and
more obvious, and the current teaching needs can not be met only by classroom, students, pen and paper, spreadsheet, and slide teaching.
This paper proposes a teaching framework based on deep reinforcement learning, which comprehensively enhances interactive teaching by
integrating agents, simulation environment and data dashboard, so that interaction is no longer limited to interaction time, interaction space
and interaction object, and then improves the usability and applicability of interactive teaching.

Keywords


deep reinforcement learning; reciprocal teaching

Full Text:

PDF

Included Database


References


[1] By Chunxiu Pei and Chunying Yang Research on interactive teaching mode [j]Journal of Hunan University of science and technology, 2007, issue 05 (5):

137-139

[2] Written by Guiling Zhao Application of traditional interactive teaching mode in network environment [j]Experimental science and technology, 2009, issue 1:

114-117

[3] Bowen, W.G., chingos, M.M., lake, K.A., & Nygren, T.I. interactive learning online at public universities: evidence from randomized trials[j]Ithaka, may

22, 2012:10-25

[4] A. oroojlooyjadid, M. Nazari, L.v. Snyder, M. Tak á C A deep q-network for the beer game: deep reinforcement learning for inventory optimization[j]

Manufacturing & service operations management, 2021:5-15

[5] R. S. Sutton and A. g. bartoReinforcement learning: an introduction[m]MIT Press, Cambridge, 1998:156-178

[6] Y. liDeep reinforcement learning: an overview[j]ArXiv preprint arxiv:1701.07274, 2017:15-23

[7] Schulman, John, et al. proximal policy optimization algorithms[j]ArXiv preprint arxiv:1707.06347, 2017:2-5

[8] J. D. stermanModeling managerial behavior: deviations of feedback in a dynamic decision making experience[j]Management science, 35 (3), 1989:321 –

339

[9] Kaelbling, Leslie P; Littman, Michael L; Moore, Andrew W. reinforcement learning: a survey[j]Journal of artistic intelligence research4, 1996: 237 – 285

[10] Bellman, R. a Markovian decision process[j]Journal of mathematics and mechanics6 (5), 1957: 679 – 684

[11] H. L. Lee, V. Padmanabhan, and s. whangInformation disturbance in a supply chain: the bullwhip eff ect[j]Management science, 43 (4), 1997:546 – 558

[12] I. giannoccaro and P. pontrandolfoInventory management in supply chains: a reinforcement learning approach[j]International Journal of production

economics, 78 (2), 2002:153 – 161

[13] S. K. chaharsooghi, J. heydari, and S. H. zegordiA reinforcement learning model for supply chain ordering management: an application to the beer

game[j]Decision support systems, 45 (4), 2008:949 – 959

[14] Ben David, Shai, kushilevitz, Eyal, Mansour, yishayOnline learning versus offl ine learning[j]Machine learning29 (1), 1997: 45 – 63

[15] Richard suttonLearning to predict by the methods of temporary diff erences[j]Machine learning3 (1), 1998: 9 – 44




DOI: https://doi.org/10.18686/esta.v10i2.419

Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 Jun Shao