Optimizing high-dimensional stochastic forestry via reinforcement learning

In proceeding beyond the generic optimal rotation model, forest economic research has applied various specifications that aim to circumvent the problems of high dimensionality. We specify an age- and size-structured mixed-species optimal harvesting model with binary variables for harvest timing, stochastic stand growth, and stochastic prices. Reinforcement learning allows solving this high-dimensional model without simplifications. In addition to presenting new features in reservation price schedules and effects of stochasticity, our setup allows evaluating the simplifications in the existing research. We find that one- or two-dimensional models lose a high fraction of attainable economic output while the commonly applied size-structured matrix model overestimates economic profitability, yields deviations in harvest timing, including optimal rotation, and dilutes the effects of stochasticity. Reinforcement learning is found to be an efficient and promising method for detailed age- and size-structured optimization models in resource economics.

DOI

10.1016/j.jedc.2022.104553

Citation

Tahvonen, O, Suominen, A, Malo, P, Viitasaari, L & Parkatti, V-P 2022, 'Optimizing high-dimensional stochastic forestry via reinforcement learning', Journal of Economic Dynamics and Control, vol. 145, 104553. https://doi.org/10.1016/j.jedc.2022.104553

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202211236560

Collections

[article-cris] Kauppakorkeakoulu / BIZ

Show all metadata

Optimizing high-dimensional stochastic forestry via reinforcement learning

Access rights

URL

Journal Title

Journal ISSN

Volume Title

Authors

Date

Department

Major/Subject

Mcode

Degree programme

Language

Pages

Series

Abstract

Description

Keywords

Other note

DOI

Citation

Permanent link to this item

Collections