This paper introduces a novel backup strategy for Monte-Carlo Tree Searc...
Deep neural networks (NNs) are known to lack uncertainty estimates and
s...
Developing reliable autonomous driving algorithms poses challenges in
te...
Reinforcement learning is able to solve complex sequential decision-maki...
Robot control for tactile feedback-based manipulation can be difficult d...
Offline goal-conditioned reinforcement learning (GCRL) can be challengin...
In goal-conditioned offline reinforcement learning, an agent learns from...
The ability to plan actions on multiple levels of abstraction enables
in...
State-of-the-art reinforcement learning (RL) algorithms typically use ra...
Offline reinforcement learning, by learning from a fixed dataset, makes ...
In many complex sequential decision making tasks, online planning is cru...
Noisy sensing, imperfect control, and environment changes are defining
c...
Curriculum reinforcement learning (CRL) aims to speed up learning of a t...
State-of-the-art deep Q-learning methods update Q-values using state
tra...
The ability of Gaussian processes (GPs) to predict the behavior of dynam...
Monte-Carlo Tree Search (MCTS) is a class of methods for solving complex...
Hierarchical reinforcement learning (HRL) proposes to solve difficult ta...
Due to recent breakthroughs, reinforcement learning (RL) has demonstrate...
We have recently proposed two pile loading controllers that learn from h...
Across machine learning, the use of curricula has shown strong empirical...
Manipulating unknown objects in a cluttered environment is difficult bec...
Optimizing a partially observable Markov decision process (POMDP) policy...
3D scene models are useful in robotics for tasks such as path planning,
...
Monte-Carlo planning and Reinforcement Learning (RL) are essential to
se...
Identifying mobile network problems in 4G cells is more challenging when...
Generalization and reuse of agent behaviour across a variety of learning...
Deep learning in combination with improved training techniques and high
...
Physically disentangling entangled objects from each other is a problem
...
Reinforcement learning with sparse rewards is still an open challenge.
C...
We consider Monte-Carlo Tree Search (MCTS) applied to Markov Decision
Pr...
Model-based Reinforcement Learning (MBRL) allows data-efficient learning...
Decentralized policies for information gathering are required when multi...
Trust-region methods have yielded state-of-the-art results in policy sea...
As robots and other intelligent agents move from simple environments and...