Optimizing High Dimensional Stochastic Forestry Viareinforcement Learning

In proceeding beyond the generic optimal rotation model, forest economic research has applied variousspecifications that aim to circumvent the problems of high dimensionality. We specify an age- andsize-structured mixed-species optimal harvesting model with binary variables for harvest timing, stochasticstand growth, and stochastic prices. Reinforcement learning allows solving this high-dimensional modelwithout simplifications. In addition to presenting new features in reservation price schedules and effects ofstochasticity, our setup allows evaluating the simplifications in the existing research. We find that one- ortwo-dimensional models lose a high fraction of attainable economic output while the commonly applied size-structuredmatrix model overestimates economic profitability, yields deviations in harvest timing, includingoptimal rotation, and dilutes the effects of stochasticity. Reinforcement learning is found to be an efficientand promising method for detailed age- and size-structured optimization models in resource economics