Responsive Safety in Reinforcement Learning

no code implementations • ICML 2020 • Adam Stooke, Joshua Achiam, Pieter Abbeel

This intuition leads to our introduction of PID control for the Lagrange multiplier in constrained RL, which we cast as a dynamical system.

reinforcement-learning Reinforcement Learning +2

Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models

no code implementations • 27 Feb 2024 • Rohit Prabhavalkar, Zhong Meng, Weiran Wang, Adam Stooke, Xingyu Cai, Yanzhang He, Arun Narayanan, Dongseong Hwang, Tara N. Sainath, Pedro J. Moreno

In the present work, we study one such strategy: applying multiple frame reduction layers in the encoder to compress encoder outputs into a small number of output frames.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Massive End-to-end Models for Short Search Queries

no code implementations • 22 Sep 2023 • Weiran Wang, Rohit Prabhavalkar, Dongseong Hwang, Qiujia Li, Khe Chai Sim, Bo Li, James Qin, Xingyu Cai, Adam Stooke, Zhong Meng, CJ Zheng, Yanzhang He, Tara Sainath, Pedro Moreno Mengibar

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 offline recognition of voice search queries, with up to 2B model parameters.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Open-Ended Learning Leads to Generally Capable Agents

no code implementations • 27 Jul 2021 • Open Ended Learning Team, Adam Stooke, Anuj Mahajan, Catarina Barros, Charlie Deck, Jakob Bauer, Jakub Sygnowski, Maja Trebacz, Max Jaderberg, Michael Mathieu, Nat McAleese, Nathalie Bradley-Schmieg, Nathaniel Wong, Nicolas Porcel, Roberta Raileanu, Steph Hughes-Fitt, Valentin Dalibard, Wojciech Marian Czarnecki

The resulting space is exceptionally diverse in terms of the challenges posed to agents, and as such, even measuring the learning progress of an agent is an open research problem.

TAG

Decoupling Representation Learning from Reinforcement Learning

3 code implementations • 14 Sep 2020 • Adam Stooke, Kimin Lee, Pieter Abbeel, Michael Laskin

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 learning.

Data Augmentation Deep Reinforcement Learning +3

Responsive Safety in Reinforcement Learning by PID Lagrangian Methods

no code implementations • 8 Jul 2020 • 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 reinforcement learning, leads to constraint-violating behavior during agent training.

reinforcement-learning Reinforcement Learning +2

Perception-Prediction-Reaction Agents for Deep Reinforcement Learning

no code implementations • 26 Jun 2020 • Adam Stooke, Valentin Dalibard, Siddhant M. Jayakumar, Wojciech M. Czarnecki, Max Jaderberg

We employ a temporal hierarchy, using a slow-ticking recurrent core to allow information to flow more easily over long time spans, and three fast-ticking recurrent cores with connections designed to create an information asymmetry.

Deep Reinforcement Learning Prediction +2

Reinforcement Learning with Augmented Data

2 code implementations • NeurIPS 2020 • Michael Laskin, Kimin Lee, Adam Stooke, Lerrel Pinto, Pieter Abbeel, Aravind Srinivas

To this end, we present Reinforcement Learning with Augmented Data (RAD), a simple plug-and-play module that can enhance most RL algorithms.

Data Augmentation OpenAI Gym +3

rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch

9 code implementations • 3 Sep 2019 • Adam Stooke, Pieter Abbeel

rlpyt is designed as a high-throughput code base for small- to medium-scale research in deep RL.

Deep Reinforcement Learning Q-Learning +2

Accelerated Methods for Deep Reinforcement Learning

8 code implementations • 7 Mar 2018 • 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.

Atari Games Deep Reinforcement Learning +2

Synkhronos: a Multi-GPU Theano Extension for Data Parallelism

1 code implementation • 11 Oct 2017 • Adam Stooke, Pieter Abbeel

We present Synkhronos, an extension to Theano for multi-GPU computations leveraging data parallelism.

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

3 code implementations • NeurIPS 2017 • Haoran Tang, Rein Houthooft, Davis Foote, Adam Stooke, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel

In this work, we describe a surprising finding: a simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks.

Atari Games continuous-control +4