Deep reinforced learning enables solving rich discrete-choice life cycle models to analyze social security reforms
This work addresses the computational bottleneck in economics for policymakers by enabling more feasible analysis of social security reforms, though it is incremental as it applies an existing method to a new domain.
The authors tackled the problem of solving complex discrete-choice life cycle models for analyzing social security reforms by comparing a deep reinforced learning algorithm (ACKTR) with dynamic programming, finding that ACKTR yields almost as good results, though with less spiked aggregate employment profiles.
Discrete-choice life cycle models of labor supply can be used to estimate how social security reforms influence employment rate. In a life cycle model, optimal employment choices during the life course of an individual must be solved. Mostly, life cycle models have been solved with dynamic programming, which is not feasible when the state space is large, as often is the case in a realistic life cycle model. Solving a complex life cycle model requires the use of approximate methods, such as reinforced learning algorithms. We compare how well a deep reinforced learning algorithm ACKTR and dynamic programming solve a relatively simple life cycle model. To analyze results, we use a selection of statistics and also compare the resulting optimal employment choices at various states. The statistics demonstrate that ACKTR yields almost as good results as dynamic programming. Qualitatively, dynamic programming yields more spiked aggregate employment profiles than ACKTR. The results obtained with ACKTR provide a good, yet not perfect, approximation to the results of dynamic programming. In addition to the baseline case, we analyze two social security reforms: (1) an increase of retirement age, and (2) universal basic income. Our results suggest that reinforced learning algorithms can be of significant value in developing social security reforms.