相关论文: Single-Peaked Domain Augmented with Complete Indif…

Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompts for all data…

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…

Dialogue research tends to distinguish between chit-chat and goal-oriented tasks. While the former is arguably more naturalistic and has a wider use of language, the latter has clearer metrics and a straightforward learning signal. Humans…

In a single-state repeated game, zero-determinant strategies can unilaterally force functions of the payoffs to take values in particular closed intervals. When the explicit use of a determinant is absent from the analysis, they are instead…

We introduce a new preference-based framework for conditional treatment effect estimation and policy learning, built on the Conditional Preference-based Treatment Effect (CPTE). CPTE requires only that outcomes be ranked under a preference…

Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment. While in real-world scenarios,…

We consider a class of reinforcement-learning systems in which the agent follows a behavior policy to explore a discrete state-action space to find an optimal policy while adhering to some restriction on its behavior. Such restriction may…

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function…

We analyze the accuracy of collective decision-making in socially connected populations, where agents update binary choices through local interactions on a network. Each agent receives a private signal that is biased -- even marginally --…

Alignment with human preferences is commonly framed using a universal reward function, even though human preferences are inherently heterogeneous. We formalize this heterogeneity by introducing user types and examine the limits of the…

In economics and social choice single-peakedness is one of the most important and commonly studied models for preferences. It is well known that single-peaked consistency for total orders is in P. However in practice a preference profile is…

Asymmetric actor-critic methods are widely used in partially observable reinforcement learning, but typically assume full state observability to condition the critic during training, which is often unrealistic in practice. We introduce the…

We study the problem of locating a single facility on a real line based on the reports of self-interested agents, when agents have double-peaked preferences, with the peaks being on opposite sides of their locations. We observe that…

We introduce the notion of a multidimensional hybrid preference domain on a (finite) set of alternatives that is a Cartesian product of finitely many components. We demonstrate that in a model of public goods provision, multidimensional…

Effective communication requires adapting to the idiosyncrasies of each communicative context--such as the common ground shared with each partner. Humans demonstrate this ability to specialize to their audience in many contexts, such as the…

The Assignment problem is a fundamental and well-studied problem in the intersection of Social Choice, Computational Economics and Discrete Allocation. In the Assignment problem, a group of agents expresses preferences over a set of items,…

In this paper we address the decision problem for a fragment of set theory with restricted quantification which extends the language studied in [4] with pair related quantifiers and constructs, in view of possible applications in the field…

A principal delegates decisions to a biased agent. Payoffs depend on a state that the principal cannot observe. Initially, the agent does not observe the state, but he can acquire information about it at a cost. We characterize the…

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…

When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…