In autonomous navigation settings, several quantities can be subject to
...
In policy learning for robotic manipulation, sample efficiency is of
par...
This work presents a novel loss function for learning nonlinear Model
Pr...
Cancer detection and classification from gigapixel whole slide images of...
We present an approach for safe trajectory planning, where a strategic t...
Despite deep-learning being state-of-the-art for data-driven model
predi...
Everyday tasks of long-horizon and comprising a sequence of multiple imp...
Implementing an autonomous vehicle that is able to output feasible, smoo...
Robots operating in human-centered environments should have the ability ...
Accurate value estimates are important for off-policy reinforcement lear...
Learning to solve complex manipulation tasks from visual observations is...
While classic control theory offers state of the art solutions in many
p...
Well-established optimization-based methods can guarantee an optimal
tra...
Challenging problems of deep reinforcement learning systems with regard ...
Clinical data from electronic medical records, registries or trials prov...
Popular Maximum Entropy Inverse Reinforcement Learning approaches requir...
In many real world applications, reinforcement learning agents have to
o...
Machine learning (ML) methods have the potential to automate clinical EE...
The common pipeline in autonomous driving systems is highly modular and
...
In the past few years, off-policy reinforcement learning methods have sh...
In many real-world decision making problems, reaching an optimal decisio...
Exploration in sparse reward reinforcement learning remains a difficult ...
Implantable, closed-loop devices for automated early detection and
stimu...
This paper deals with the reality gap from a novel perspective, targetin...
As autonomous service robots become more affordable and thus available a...
We present an approach for agents to learn representations of a global m...
In this paper we consider the problem of robot navigation in simple maze...
We introduce Embed to Control (E2C), a method for model learning and con...
We review attempts that have been made towards understanding the
computa...