We analyze the performance of heterogeneous learning agents in asset markets with stochastic payoffs. Agents aim to maximize the expected growth rate of their wealth but have different theories on how to learn to do this best. Our main focus is on comparing Bayesian learners and no-regret learners who compete in markets and identifying the conditions under which each approach is more effective. Bayesian learners with a finite prior that assigns positive probability to the correct model have posterior beliefs that converge exponentially fast, and such agents survive even in the presence of agents who invest according to the correct model. Bayesian learners with a continuum prior converge at a slower rate of O((logT)/T).

In this paper, we introduce a novel approach to repeated auctions that accounts for bidders' temporal preferences, important in applications such as advertising. In our model, when a player wins an auction after not winning for ℓ rounds, she is awarded r(ℓ) utility and her goal is to maximize her total utility. r : ℕ → ℝ ≥0 satisfies the following properties. (i) The more rounds without a win, the higher the reward, i.e., r is weakly increasing. (ii) As more rounds pass without winning, the increase in reward becomes smaller, i.e., r is concave. The motivation behind these properties comes from the advertising literature, which states that an increased frequency of winning builds advertising effectiveness at a decreasing (but not declining) rate. The above properties guarantee that adding more wins to any sequence of winning intervals increases the total reward.

Real-life contractual relations typically involve repeated interactions between the principal and agent, where, despite theoretical appeal, players rarely use complex dynamic strategies and instead manage uncertainty through learning algorithms. In this paper, we initiate the study of repeated contracts with learning agents, focusing on those achieving no-regret outcomes. For the canonical setting where the agent’s actions result in success or failure, we present a simple, optimal solution for the principal: Initially provide a linear contract with scalar $\alpha > 0$, then switch to a zero-scalar contract. This shift causes the agent to “free-fall” through their action space, yielding non-zero rewards for the principal at zero cost. Interestingly, despite the apparent exploitation, there are instances where our dynamic contract can make \emph{both} players better off compared to the best static contract. We then broaden the scope of our results to general linearly-scaled contracts, and, finally, to the best of our knowledge, we provide the first analysis of optimization against learning agents with uncertainty about the time horizon.

We study Proportional Response Dynamics (PRD) in linear Fisher markets, where participants act asynchronously. We model this scenario as a sequential process in which at each step, an adversary selects a subset of the players to update their bids, subject to liveness constraints. We show that if every bidder individually applies the PRD update rule whenever they are included in the group of bidders selected by the adversary, then, in the generic case, the entire dynamic converges to a competitive equilibrium of the market. Our proof technique reveals additional properties of linear Fisher markets, such as the uniqueness of the market equilibrium for generic parameters and the convergence of associated no swap regret dynamics and best response dynamics under certain conditions.

Understanding the emerging behaviors of reinforcement learning agents may be difficult because such agents are often trained using highly complex and expressive models. In recent years, most approaches developed for explaining agent behaviors rely on domain knowledge or on an analysis of the agent’s learned policy. For some domains, relevant knowledge may not be available or may be insufficient for producing meaningful explanations. We suggest using formal model abstractions and transforms, previously used mainly for expediting the search for optimal policies, to automatically explain discrepancies that may arise between the behavior of an agent and the behavior that is anticipated by an observer. We formally define this problem of Reinforcement Learning Policy Explanation(RLPE), suggest a class of transforms which can be used for explaining emergent behaviors, and suggest meth-ods for searching efficiently for an explanation. We demonstrate the approach on standard benchmarks.

Understanding emerging behaviors of reinforcement learning (RL) agents may be difficult since such agents are often trained in complex environments using highly complex decision making procedures. This has given rise to a variety of approaches to explainability in RL that aim to reconcile discrepancies that may arise between the behavior of an agent and the behavior that is anticipated by an observer. Most recent approaches have relied either on domain knowledge, that may not always be available, on an analysis of the agent’s policy, or on an analysis of specific elements of the underlying environment, typically modeled as a Markov Decision Process (MDP). Our key claim is that even if the underlying model is not fully known (e.g., the transition probabilities have not been accurately learned) or is not maintained by the agent (i.e., when using model-free methods), the model can nevertheless be exploited to automatically generate explanations. For this purpose, we suggest using formal MDP abstractions and transforms, previously used in the literature for expediting the search for optimal policies, to automatically produce explanations. Since such transforms are typically based on a symbolic representation of the environment, they can provide meaningful explanations for gaps between the anticipated and actual agent behavior. We formally define the explainability problem, suggest a class of transforms that can be used for explaining emergent behaviors, and suggest methods that enable efficient search for an explanation. We demonstrate the approach on a set of standard benchmarks.

The usage of automated learning agents is becoming increasingly prevalent in many online economic applications such as online auctions and automated trading. Motivated by such applications, this paper is dedicated to fundamental modeling and analysis of the strategic situations that the users of automated learning agents are facing. We consider strategic settings where several users engage in a repeated online interaction, assisted by regret-minimizing learning agents that repeatedly play a "game" on their behalf. We propose to view the outcomes of the agents' dynamics as inducing a "meta-game" between the users. Our main focus is on whether users can benefit in this meta-game from "manipulating" their own agents by misreporting their parameters to them. We define a general framework to model and analyze these strategic interactions between users of learning agents for general games and analyze the equilibria induced between the users in three classes of games. We show that, generally, users have incentives to misreport their parameters to their own agents, and that such strategic user behavior can lead to very different outcomes than those anticipated by standard analysis.

We study a market of investments on networks, where each agent (vertex) can invest in any enterprise linked to her, and at the same time, raise capital for her firm’s enterprise from other agents she is linked to. Failing to raise sufficient capital results with the firm defaulting, being unable to invest in others. Our main objective is to examine the role of collateral contracts in handling the strategic risk that can propagate to a systemic risk throughout the network in a cascade of defaults. We take a mechanism-design approach and solve for the optimal scheme of collateral contracts that capital raisers offer their investors. These contracts aim at sustaining the efficient level of investment as a unique Nash equilibrium, while minimizing the total collateral.

We analyze a scenario in which software agents implemented as regret-minimizing algorithms engage in a repeated auction on behalf of their users. We study first-price and second-price auctions, as well as their generalized versions (e.g., as those used for ad auctions). Using both theoretical analysis and simulations, we show that, surprisingly, in second-price auctions the players have incentives to misreport their true valuations to their own learning agents, while in first-price auctions it is a dominant strategy for all players to truthfully report their valuations to their agents.

We consider the problem of predicting human players' actions in repeated strategic interactions. Our goal is to predict the dynamic step-by-step behavior of individual players in previously unseen games. We study the ability of neural networks to perform such predictions and the information that they require. We show on a dataset of normal-form games from experiments with human participants that standard neural networks are able to learn functions that provide more accurate predictions of the players' actions than established models from behavioral economics. The networks outperform the other models in terms of prediction accuracy and cross-entropy, and yield higher economic value. We show that if the available input is only of a short sequence of play, economic information about the game is important for predicting behavior of human agents. However, interestingly, we find that when the networks are trained with long enough sequences of history of play, action-based networks do well and additional economic details about the game do not improve their performance, indicating that the sequence of actions encode sufficient information for the success in the prediction task.