322 citations · 877 across the 12 of their papers we have counts for
12 papers
Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers
Adam Stooke, Rohit Prabhavalkar, Khe Chai Sim +1
Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter t…
Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
Rohit Prabhavalkar, Zhong Meng, Weiran Wang +7
The accuracy of end-to-end (E2E) automatic speech recognition (ASR) models continues to improve as they are scaled to larger sizes, with some now reaching billions of parameters. W…
Massive End-to-end Models for Short Search Queries
Weiran Wang, Rohit Prabhavalkar, Dongseong Hwang +11
In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for of…
Open-Ended Learning Leads to Generally Capable Agents
Open Ended Learning Team, Adam Stooke, Anuj Mahajan +15
In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We…
Decoupling Representation Learning from Reinforcement Learning
Adam Stooke, Kimin Lee, Pieter Abbeel +1
In an effort to overcome limitations of reward-driven feature learning in deep reinforcement learning (RL) from images, we propose decoupling representation learning from policy le…
Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Adam Stooke, Joshua Achiam, Pieter Abbeel
Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe rein…
Perception-Prediction-Reaction Agents for Deep Reinforcement Learning
Adam Stooke, Valentin Dalibard, Siddhant M. Jayakumar +2
We introduce a new recurrent agent architecture and associated auxiliary losses which improve reinforcement learning in partially observable tasks requiring long-term memory. We em…
Reinforcement Learning with Augmented Data
Michael Laskin, Kimin Lee, Adam Stooke +3
Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks…
rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
Adam Stooke, Pieter Abbeel
Since the recent advent of deep reinforcement learning for game play and simulated robotic control, a multitude of new algorithms have flourished. Most are model-free algorithms wh…
Accelerated Methods for Deep Reinforcement Learning
Adam Stooke, Pieter Abbeel
Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-around time remains a key bottleneck in research and in practice. We investigate how to opt…
Synkhronos: a Multi-GPU Theano Extension for Data Parallelism
Adam Stooke, Pieter Abbeel
We present Synkhronos, an extension to Theano for multi-GPU computations leveraging data parallelism. Our framework provides automated execution and synchronization across devices,…
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Haoran Tang, Rein Houthooft, Davis Foote +6
Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov d…