no code implementations • 31 Mar 2022 • Steven Bohez, Saran Tunyasuvunakool, Philemon Brakel, Fereshteh Sadeghi, Leonard Hasenclever, Yuval Tassa, Emilio Parisotto, Jan Humplik, Tuomas Haarnoja, Roland Hafner, Markus Wulfmeier, Michael Neunert, Ben Moran, Noah Siegel, Andrea Huber, Francesco Romano, Nathan Batchelor, Federico Casarini, Josh Merel, Raia Hadsell, Nicolas Heess
We investigate the use of prior knowledge of human and animal movement to learn reusable locomotion skills for real legged robots.
Imitation learning circumvents this problem and has been used with motion capture data to extract quadruped gaits for flat terrains.
We propose a framework that uses a multi-objective RL algorithm to find a Pareto front of policies that trades off between the reward and constraint(s), and simultaneously searches along this front for constraint-satisfying policies.
In many environments only a tiny subset of all states yield high reward.
A field that has directly benefited from the recent advances in deep learning is Automatic Speech Recognition (ASR).
Ranked #6 on Speech Recognition on TIMIT
First, we suggest to remove the reset gate in the GRU design, resulting in a more efficient single-gate architecture.
Improving distant speech recognition is a crucial step towards flexible human-machine interfaces.
Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and reverberation are met.
Meanwhile, Connectionist Temporal Classification (CTC) with Recurrent Neural Networks (RNNs), which is proposed for labeling unsegmented sequences, makes it feasible to train an end-to-end speech recognition system instead of hybrid settings.
We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL).
Ranked #8 on Machine Translation on IWSLT2015 English-German
Although the empirical results are impressive, the Ladder Network has many components intertwined, whose contributions are not obvious in such a complex architecture.
Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs).