Reinforcement Learning (RL) has shown promising results learning policie...
It is well known that Reinforcement Learning (RL) can be formulated as a...
We introduce a novel setting, wherein an agent needs to learn a task fro...
Humans use audio signals in the form of spoken language or verbal reacti...
The utility of reinforcement learning is limited by the alignment of rew...
We introduce an offline reinforcement learning (RL) algorithm that expli...
We propose a new framework for imitation learning - treating imitation a...
Many sequential decision making problems are high-stakes and require
off...
The goal of offline reinforcement learning (RL) is to find an optimal po...
We propose a method that efficiently learns distributions over articulat...
We explore methodologies to improve the robustness of generative adversa...
Imitation learning and instruction-following are two common approaches t...
Learning with an objective to minimize the mismatch with a reference
dis...
When faced with sequential decision-making problems, it is often useful ...
We propose a novel reinforcement learning framework that performs
self-s...
We introduce a sample-efficient method for learning state-dependent stif...
As humans interact with autonomous agents to perform increasingly
compli...
Reactions such as gestures, facial expressions, and vocalizations are an...
Robots in human environments will need to interact with a wide variety o...
Reinforcement learning (RL), particularly in sparse reward settings, oft...
One of the main challenges in imitation learning is determining what act...
Human gaze is known to be an intention-revealing signal in human
demonst...
Bayesian reward learning from demonstrations enables rigorous safety and...
A central goal of meta-learning is to find a learning rule that enables ...
Bayesian inverse reinforcement learning (IRL) methods are ideal for safe...
Sudden changes in the dynamics of robotic tasks, such as contact with an...
Human gaze is known to be a strong indicator of underlying human intenti...
The performance of imitation learning is typically upper-bounded by the
...
A key challenge in intelligent robotics is creating robots that are capa...
Deep reinforcement learning encompasses many versatile tools for designi...
Estimating statistical uncertainties allows autonomous agents to communi...
A critical flaw of existing inverse reinforcement learning (IRL) methods...
Recent reinforcement learning (RL) approaches have shown strong performa...
Active learning from demonstration allows a robot to query a human for
s...
When developing general purpose robots, the overarching software archite...
Robots operating in real-world human environments will likely encounter ...
Due to burdensome data requirements, learning from demonstration often f...
In reinforcement learning, off-policy evaluation is the task of using da...
Inverse reinforcement learning (IRL) infers a reward function from
demon...
Noisy observations coupled with nonlinear dynamics pose one of the bigge...
Noisy observations coupled with nonlinear dynamics pose one of the bigge...
Reinforcement learning algorithms discover policies that maximize reward...
In the field of reinforcement learning there has been recent progress to...
We consider the task of evaluating a policy for a Markov decision proces...
For an autonomous agent, executing a poor policy may be costly or even
d...