Related papers: Conditional Recall
In many real-world games, such as traders repeatedly bargaining with customers, it is very hard for a single AI trader to make good deals with various customers in a few turns, since customers may adopt different strategies even the…
I model a rational agent who experiences endogenous deadline pressure in the face of a fixed future deadline. The agent holds a resource stock, and opportunities to spend resources arise randomly according to a Poisson process. When the…
Over more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention. While recurrent models aim to compress the data into a fixed-size memory (called hidden state), attention…
People learn throughout life. However, incrementally updating conventional neural networks leads to catastrophic forgetting. A common remedy is replay, which is inspired by how the brain consolidates memory. Replay involves fine-tuning a…
We consider a dynamic moral hazard problem between a principal and an agent, where the sole instrument the principal has to incentivize the agent is the disclosure of information. The principal aims at maximizing the (discounted) number of…
Deep reinforcement learning (DRL) agents excel in solving complex decision-making tasks across various domains. However, they often require a substantial number of training steps and a vast experience replay buffer, leading to significant…
Motivated by applications to online advertising and recommender systems, we consider a game-theoretic model with delayed rewards and asynchronous, payoff-based feedback. In contrast to previous work on delayed multi-armed bandits, we focus…
Due to the importance of artificial intelligence (AI) in a variety of high-stakes decisions, such as loan approval, job hiring, and criminal bail, researchers in Explainable AI (XAI) have developed algorithms to provide users with recourse…
The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, the sub-field of Class-Incremental Continual Learning fosters…
We study reinforcement learning (RL) with transition look-ahead, where the agent may observe which states would be visited upon playing any sequence of $\ell$ actions before deciding its course of action. While such predictive information…
While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation. To address this, we introduce…
We conducted an experiment where participants played a perfect-information game against a computer, which was programmed to deviate often from its backward induction strategy right at the beginning of the game. Participants knew that in…
John Wheeler devised a gedanken experiment in which a piece of apparatus can be altered just before the arrival of particle, and this ``delayed choice'' can, seemingly, alter the quantum state of the particle at a much earlier time, long…
Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…
Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take action against an undesirable outcome made by an…
Adequately assigning credit to actions for future outcomes based on their contributions is a long-standing open challenge in Reinforcement Learning. The assumptions of the most commonly used credit assignment method are disadvantageous in…
Commitments play a crucial role in game theory, shaping strategic interactions by either altering a player's own payoffs or influencing the incentives of others through outcome-contingent payments. While most research has focused on using…
We study a class of determinantal ideals that are related to conditional independence (CI) statements with hidden variables. Such CI statements correspond to determinantal conditions on a matrix whose entries are probabilities of events…
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence. Existing cognitive science literature on defeasible reasoning suggests that a person forms a mental model of the problem…
Prioritized experience replay is a reinforcement learning technique whereby agents speed up learning by replaying useful past experiences. This usefulness is quantified as the expected gain from replaying the experience, a quantity often…