The majority of algorithms involve building an explicit map during an exploration phase and then planning and acting via that representation. In this work, we are interested in pushing the limits of end-to-end deep reinforcement learning for navigation by proposing new methods and demonstrating their performance in large-scale, real-world environments.

Neural Information Processing Systems http://nips.cc/

We introduce DeepProbLog, a probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques can be adapted for the new language. Our experiments demonstrate that DeepProbLog supports (i) both symbolic and sub-symbolic representations and inference, (ii) program induction, (iii) probabilistic (logic) programming, and (iv) (deep) learning from examples. To the best of our knowledge, this work is the first to propose a framework where general-purpose neural networks and expressive probabilistic-logical modeling and reasoning are integrated in a way that exploits the full expressiveness and strengths of both worlds and can be trained end-to-end based on examples.

While the term "context" is

Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties.

Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling.

This enables us to deploy such models for continuous real-time prediction on devices as small as a Raspberry Pi0 and Arduino variants, a task that the baseline LSTM could not achieve.

Among those variational regularization models are one of the most popular approaches.

Experiments on multiple benchmarks show the advantage of our method compared to strong baselines.

We demonstrate empirically the effectiveness of our theoretical results in predicting when networks are able to start training.