Although conversational AIs have demonstrated fantastic performance, the...
The difficulty of manually specifying reward functions has led to an int...
Standard model-based reinforcement learning (MBRL) approaches fit a
tran...
We introduce Ideograph, a language for expressing and manipulating struc...
Prediction sets have recently been shown to be a promising strategy for
...
Compositional reinforcement learning is a promising approach for trainin...
Real-world processes often contain intermediate state that can be modele...
Blockchains with smart contracts are distributed ledger systems which ac...
We study the problem of allocating limited supply of medical resources i...
We describe the current content moderation strategy employed by Meta to
...
Uncertainty quantification is a key component of machine learning models...
Offline goal-conditioned reinforcement learning (GCRL) promises
general-...
Reinforcement learning has been shown to be an effective strategy for
au...
We give a simple, generic conformal prediction method for sequential
pre...
A key challenge facing natural language interfaces is enabling users to
...
Accurately detecting and tracking multi-objects is important for
safety-...
Environments with sparse rewards and long horizons pose a significant
ch...
A key feature of human intelligence is the ability to generalize beyond ...
We propose State Matching Offline DIstribution Correction Estimation
(SM...
Reinforcement Learning (RL) agents in the real world must satisfy safety...
A key challenge to deploying reinforcement learning in practice is explo...
Ensuring safety for human-interactive robotics is important due to the
p...
We study the problem of synthesizing programs that include machine learn...
A key challenge facing deep learning is that neural networks are often n...
A key aspect of human intelligence is their ability to convey their know...
Many reinforcement learning (RL) problems in practice are offline, learn...
We study the problem of learning control policies for complex tasks give...
An important challenge facing modern machine learning is how to rigorous...
Sparse regression has recently been applied to enable transfer learning ...
In this paper, we propose a new technique based on program synthesis for...
Video-based sensing from aerial drones, especially small multirotor dron...
A key challenge for reinforcement learning is solving long-horizon plann...
We study the problem of inferring communication structures that can solv...
For autonomous cars to drive safely and effectively, they must anticipat...
As machine learning black boxes are increasingly being deployed in real-...
As machine learning models are increasingly deployed in high-stakes doma...
A key challenge for deploying deep neural networks (DNNs) in safety crit...
We propose a novel hierarchical reinforcement learning framework for con...
Reinforcement learning is a promising approach for learning control poli...
Reliable uncertainty estimates are an important tool for helping autonom...
We propose an algorithm combining calibrated prediction and generalizati...
We propose a novel approach to program synthesis, focusing on synthesizi...
As machine learning black boxes are increasingly being deployed in criti...
Reinforcement learning is a promising approach to learning control polic...
This paper proposes a framework for safe reinforcement learning that can...
In this paper, we present a learning approach to goal assignment and
tra...
Reinforcement learning is a promising approach to learning control polic...
The increasing prevalence of mobile apps has led to a proliferation of
r...
Machine learning has shown much promise in helping improve the quality o...
It has recently been shown that if feedback effects of decisions are ign...