Working Papers
Recommender systems and efficient social learning (Draft)
Abstract: In this paper, I study a model of a streaming platform (for instance YouTube or Netflix) with a catalog of items whose quality are unknown. Short-lived users arrive in sequence and browse the catalog, paying a small cost each time they want to examine a new alternative. The platform observes their behavior and uses it to deduce information about the items' quality so as to enhance future user's experience. I show that the platform is able to distinguish high-quality items if and only if a condition linking the cost of browsing and the thickness of the tail of the distribution from which the quality of the items is drawn holds true. This condition relates to the ability of the platform to incentivize users to explore new items using the information gathered with the previous users. I pin down an easily implementable policy that guarantees efficient learning.
Algorithmic collusion with endogenous exploration (Draft)
Abstract: I study a two-stage model in which two players simultaneously choose an exploration parameter for their Q-learning algorithms, which then repeatedly play a one-shot game chosen from a class of social dilemmas including the prisoner's dilemma, first and second price auctions as well as Bertrand competition with horizontally differentiated products. The players collect the limit average payoffs obtained by their algorithms. I show that all equilibria are collusive : both players receive payoffs that are strictly higher than the payoffs received in the unique strict Nash equilibrium of the one-shot game. I then use extensive numerical simulations in a Bertrand duopoly and a parameterized prisoner's dilemma. Their results allow to gain insight on (i) the mechanism causing algorithmic collusion and (ii) the strategic role of exploration levels in the game. They reveal that in equilibrium, the players tend to choose algorithms that over-explore, which comes at the detriment of joint payoff. These findings have important implications for algorithmic collusion.
Algorithmic collusion under asynchronous price updating (with G. Abel and A. Kalogeratos) (Draft)
Abstract: This paper investigates the effect of asynchrony in agents' updates in the emergence of algorithmic collusion. We present a continuous-time model for algorithmic collusion in which two firms use Q-learning algorithms to set prices asynchronously in a Bertrand duopoly. The firms update their prices at times dictated by a Poisson clock. By controlling the extent of agents' asynchrony, we run extensive numerical experiments with three specifications of the algorithm to investigate the emergence of algorithmic collusion. The strength of collusion is measured by a standard collusion index, as well as by automatically detecting the reward-punishment schemes. This is done by recording a large number of algorithms' reactions to unilateral price cuts and comparing them with the reactions of untrained algorithms. Our findings indicate that asynchrony hampers collusion, especially when the algorithms are stateless. When they condition on their competitor's previous prices, the sensitivity of algorithmic collusion to asynchrony varies depending on the type of information they have access to. The implications of these results for the regulation of algorithmic pricing are discussed.
On the effect of asynchronous updates in social dilemmas (with G. Abel and A. Kalogeratos) (Draft coming soon)
Abstract: The rise of agentic artificial intelligence has given birth to a multitude of technological advances, such as artificial intelligence assistants, social network bots, and algorithmic agents that start taking over sensitive practices like algorithmic pricing. This has led to a growing interest in understanding how autonomous agents can learn to interact with their peers and their environment. In this article, we use a 𝑄-learning framework for understanding cooperation dynamics in social dilemmas, where individually rational choices lead to collectively suboptimal outcomes. In particular, we argue that introducing randomness in action updates can better describe several phenomena observed in real-world social dilemmas, such as asynchrony and imbalance in update rates. Exploration of the parameter space in different games reveals that uncertainty in learning strategies deters cooperation. This is in contrast to the existing literature that has been reporting that more uncertainty leads to better cooperative outcomes. Notably, we also find that individual payoff is maximized when agents update their actions at the same rate, indicating that synchrony in action updates is beneficial for cooperation. Our findings provide new insights into the dynamics of cooperation in social dilemmas and highlight the importance of considering randomness in learning strategies.
Published Papers
Work in progress
Sequential search with endogenous entry