Related papers: Interactive Model Expansion in an Observable Envir…
Information exploration tasks are inherently complex, ill-structured, and involve sequences of actions usually spread over many sessions. When exploring a dataset, users tend to experiment higher degrees of uncertainty, mostly raised by…
Assessing the systemic effects of uncertainty that arises from agents' partial observation of the true states of the world is critical for understanding a wide range of scenarios. Yet, previous modeling work on agent learning and…
In this work we consider partially observable environments with sparse rewards. We present a self-supervised representation learning method for image-based observations, which arranges embeddings respecting temporal distance of…
Recent work has shown how predictive modeling can endow agents with rich knowledge of their surroundings, improving their ability to act in complex environments. We propose question-answering as a general paradigm to decode and understand…
The ability to predict a user's information need would have wide-ranging implications, from saving time and effort to mitigating vocabulary gaps. We study how to interactively predict a user's information need by letting them select a…
Explicit information seeking is essential to human problem-solving in practical environments characterized by incomplete information and noisy dynamics. When the true environmental state is not directly observable, humans seek information…
Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempts to decode the mappings between utterances and situations.…
To generalize across tasks, an agent should acquire knowledge from past tasks that facilitate adaptation and exploration in future tasks. We focus on the problem of in-context adaptation and exploration, where an agent only relies on…
This paper addresses the problem of both actively searching and tracking multiple unknown dynamic objects in a known environment with multiple cooperative autonomous agents with partial observability. The tracking of a target ends when the…
Some instances of creative thinking require an agent to build and test hypothetical theories. Such a reasoner needs to explore the space of not only those situations that have occurred in the past, but also those that are rationally…
We consider apprenticeship learning, i.e., having an agent learn a task by observing an expert demonstrating the task in a partially observable environment when the model of the environment is uncertain. This setting is useful in…
As researchers and practitioners of applied machine learning, we are given a set of requirements on the problem to be solved, the plausibly obtainable data, and the computational resources available. We aim to find (within those bounds)…
Artificial intelligence applications such as industrial robotics, military surveillance, and hazardous environment clean-up, require situation understanding based on partial, uncertain, and ambiguous or erroneous evidence. It is necessary…
A combination of deep reinforcement learning and supervised learning is proposed for the problem of active sequential hypothesis testing in completely unknown environments. We make no assumptions about the prior probability, the action and…
Bayesian methods are useful for statistical inference. However, real-world problems can be challenging using Bayesian methods when the data analyst has only limited prior knowledge. In this paper we consider a class of problems, called…
For arbitrary linear time-invariant systems, the existence of a strong functional observer is investigated. Such observer determines, from the available measurement on the plant, an estimate of a function of the state and the input. This…
We consider online learning problems under a partial observability model capturing situations where the information conveyed to the learner is between full information and bandit feedback. In the simplest variant, we assume that in addition…
Open ad hoc teamwork is the problem of training a single agent to efficiently collaborate with an unknown group of teammates whose composition may change over time. A variable team composition creates challenges for the agent, such as the…
In this work, we introduce the concept of Active Representation Learning, a novel class of problems that intertwines exploration and representation learning within partially observable environments. We extend ideas from Active Simultaneous…
It is known that statistical model selection as well as identification of dynamical equations from available data are both very challenging tasks. Physical systems behave according to their underlying dynamical equations which, in turn, can…