Publication details
Payoff size variation problem in simple reinforcement learning algorithms
| Authors | |
|---|---|
| Year of publication | 2013 |
| Type | Article in Proceedings |
| Conference | Proceedings of the 31st International Conference Mathematical Methods in Economics 2013 |
| MU Faculty or unit | |
| Citation | |
| Field | Economy |
| Keywords | reinforcement learning; agent-based simulation; economic experiments; voluntary provision of public goods |
| Attached files | |
| Description | This paper shows that the speed of the reinforcement learning depends on the size of the payoffs, at least when all payoffs are positive. When the speed of learning is too fast, the agents tend to learn to play the actions which they randomly chosen in the first rounds of the learning process. The compositions of the agents’ strategies then on the aggregate level resembles the initial individual agent’s mixed strategy. This may create artificial effects in the simulations where the size of payoffs depend on the model treatments because the speed of learning cannot be tuned in. |
| Related projects: |