We present a novel approach to address the challenge of generalization i...
Experimentation on real robots is demanding in terms of time and costs. ...
Language Models and Vision Language Models have recently demonstrated
un...
Optimizing for humans' latent preferences is a grand challenge in route
...
We investigate whether Deep Reinforcement Learning (Deep RL) is able to
...
The ability to effectively reuse prior knowledge is a key requirement wh...
While there has been substantial success in applying actor-critic method...
The ability to discover useful behaviours from past experience and trans...
Robots will experience non-stationary environment dynamics throughout th...
We investigate the use of prior knowledge of human and animal movement t...
Offline Reinforcement Learning (ORL) enablesus to separately study the t...
For robots operating in the real world, it is desirable to learn reusabl...
Complex sequential tasks in continuous-control settings often require ag...
Reinforcement learning (RL) for continuous control typically employs
dis...
Curiosity-based reward schemes can present powerful exploration mechanis...
Intelligent behaviour in the physical world exhibits structure at multip...
Projecting high-dimensional environment observations into lower-dimensio...
Robot manipulation requires a complex set of skills that need to be care...
Modern Reinforcement Learning (RL) algorithms promise to solve difficult...
Solutions to most complex tasks can be decomposed into simpler, intermed...
Modern reinforcement learning algorithms can learn solutions to increasi...
Many real-world control problems involve both discrete decision variable...
Applying reinforcement learning (RL) to physical systems presents notabl...
The successful application of flexible, general learning algorithms -- s...
Recent successes in machine learning have led to a shift in the design o...
Due to recent advances - compute, data, models - the role of learning in...
Model interpretability and systematic, targeted model adaptation present...
Many advanced Learning from Demonstration (LfD) methods consider the
dec...
Continuous appearance shifts such as changes in weather and lighting
con...
Continuous appearance shifts such as changes in weather and lighting
con...
Training robots for operation in the real world is a complex, time consu...
Many relevant tasks require an agent to reach a certain state, or to
man...
Recent advances have shown the capability of Fully Convolutional Neural
...