Picture for Adam Stooke

Adam Stooke

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

Add code
Feb 27, 2024
Figure 1 for Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
Figure 2 for Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
Figure 3 for Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
Figure 4 for Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
Viaarxiv icon

Massive End-to-end Models for Short Search Queries

Add code
Sep 22, 2023
Figure 1 for Massive End-to-end Models for Short Search Queries
Figure 2 for Massive End-to-end Models for Short Search Queries
Figure 3 for Massive End-to-end Models for Short Search Queries
Figure 4 for Massive End-to-end Models for Short Search Queries
Viaarxiv icon

Open-Ended Learning Leads to Generally Capable Agents

Add code
Jul 31, 2021
Figure 1 for Open-Ended Learning Leads to Generally Capable Agents
Figure 2 for Open-Ended Learning Leads to Generally Capable Agents
Figure 3 for Open-Ended Learning Leads to Generally Capable Agents
Figure 4 for Open-Ended Learning Leads to Generally Capable Agents
Viaarxiv icon

Decoupling Representation Learning from Reinforcement Learning

Add code
Sep 30, 2020
Figure 1 for Decoupling Representation Learning from Reinforcement Learning
Figure 2 for Decoupling Representation Learning from Reinforcement Learning
Figure 3 for Decoupling Representation Learning from Reinforcement Learning
Figure 4 for Decoupling Representation Learning from Reinforcement Learning
Viaarxiv icon

Responsive Safety in Reinforcement Learning by PID Lagrangian Methods

Add code
Jul 08, 2020
Figure 1 for Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Figure 2 for Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Figure 3 for Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Figure 4 for Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Viaarxiv icon

Perception-Prediction-Reaction Agents for Deep Reinforcement Learning

Add code
Jun 26, 2020
Figure 1 for Perception-Prediction-Reaction Agents for Deep Reinforcement Learning
Figure 2 for Perception-Prediction-Reaction Agents for Deep Reinforcement Learning
Figure 3 for Perception-Prediction-Reaction Agents for Deep Reinforcement Learning
Figure 4 for Perception-Prediction-Reaction Agents for Deep Reinforcement Learning
Viaarxiv icon

Reinforcement Learning with Augmented Data

Add code
May 11, 2020
Figure 1 for Reinforcement Learning with Augmented Data
Figure 2 for Reinforcement Learning with Augmented Data
Figure 3 for Reinforcement Learning with Augmented Data
Figure 4 for Reinforcement Learning with Augmented Data
Viaarxiv icon

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

Add code
Sep 24, 2019
Figure 1 for rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
Figure 2 for rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
Figure 3 for rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
Figure 4 for rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
Viaarxiv icon

Accelerated Methods for Deep Reinforcement Learning

Add code
Mar 07, 2018
Figure 1 for Accelerated Methods for Deep Reinforcement Learning
Figure 2 for Accelerated Methods for Deep Reinforcement Learning
Figure 3 for Accelerated Methods for Deep Reinforcement Learning
Figure 4 for Accelerated Methods for Deep Reinforcement Learning
Viaarxiv icon

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

Add code
Dec 05, 2017
Figure 1 for #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Figure 2 for #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Figure 3 for #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Figure 4 for #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Viaarxiv icon