Cooperative Multi-agent Reinforcement Learning (MARL) algorithms with
Ze...
Egocentric gaze anticipation serves as a key building block for the emer...
Humans learn quickly even in tasks that contain complex visual informati...
Due to the significant computational challenge of training large-scale g...
Persuasion modeling is a key building block for conversational agents.
E...
Multiagent learning settings are inherently more difficult than single-a...
Machine learning problems with multiple objective functions appear eithe...
In this paper, we present the first transformer-based model to address t...
We introduce the novel problem of anticipating a time series of future h...
The main challenge of multiagent reinforcement learning is the difficult...
AI planning and Reinforcement Learning (RL) both solve sequential
decisi...
In this paper, a novel distributed scheduling algorithm is proposed, whi...
This paper investigates the throughput performance issue of the
relay-as...
Many works in explainable AI have focused on explaining black-box
classi...
Hierarchical reinforcement learning has focused on discovering temporall...
Given a video captured from a first person perspective and recorded in a...
To understand human daily social interaction from egocentric perspective...
This paper introduces an information-theoretic constraint on learned pol...
A fundamental challenge in multiagent reinforcement learning is to learn...
Biological agents learn and act intelligently in spite of a highly limit...
We address the task of jointly determining what a person is doing and wh...
In this paper, we characterize the performance of and develop thermal
ma...
The options framework is a popular approach for building temporally exte...
We address the challenging task of anticipating human-object interaction...
We address the challenging problem of learning motion representations us...
Heterogeneous knowledge naturally arises among different agents in
coope...
Lack of performance when it comes to continual learning over non-station...
Building systems that autonomously create temporal abstractions from dat...
Over two hundreds health awareness events take place in the United State...
We present a framework and algorithm for peer-to-peer teaching in cooper...
Eigenoptions (EOs) have been recently introduced as a promising idea for...
Options in reinforcement learning allow agents to hierarchically decompo...
This paper presents a data-driven approach for multi-robot coordination ...
This paper presents the first ever approach for solving
continuous-obser...
Robust environment perception is essential for decision-making on robots...
Expectation maximization (EM) has recently been shown to be an efficient...
This paper presents a novel algorithm, based upon the dependent Dirichle...