papers

Publications (11)

cs.LG2021

ETA Prediction with Graph Neural Networks in Google Maps

Austin Derrow-Pinion, Jennifer She, David Wong +14

Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time…

cs.AI2011

A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control

Todd Hester, Michael Quinlan, Peter Stone

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practic…

cs.LG2018

Observe and Look Further: Achieving Consistent Performance on Atari

Tobias Pohlen, Bilal Piot, Todd Hester +10

Despite significant advances in the field of deep Reinforcement Learning (RL), today's algorithms still fail to learn human-level policies consistently over a set of diverse tasks…

cs.RO2018

A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning

Mel Vecerik, Oleg Sushkov, David Barker +3

Insertion is a challenging haptic and visual control problem with significant practical value for manufacturing. Existing approaches in the model-based robotics community can be hi…

cs.LG2016

Adaptive Lambda Least-Squares Temporal Difference Learning

Timothy A. Mann, Hugo Penedones, Shie Mannor +1

Temporal Difference learning or TD() is a fundamental algorithm in the field of reinforcement learning. However, setting TD's parameter, which controls the timescale of TD…

cs.AI2018

Safe Exploration in Continuous Action Spaces

Gal Dalal, Krishnamurthy Dvijotham, Matej Vecerik +3

We address the problem of deploying a reinforcement learning (RL) agent on a physical system such as a datacenter cooling unit or robot, where critical constraints must never be vi…

cs.AI2018

Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards

Mel Vecerik, Todd Hester, Jonathan Scholz +7

We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algor…

cs.AI2017

Deep Q-learning from Demonstrations

Todd Hester, Matej Vecerik, Olivier Pietquin +11

Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of dat…

cs.LG2020

Robust Reinforcement Learning for Continuous Control with Model Misspecification

Daniel J. Mankowitz, Nir Levine, Rae Jeong +7

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcem…

cs.LG2021

An empirical investigation of the challenges of real-world reinforcement learning

Gabriel Dulac-Arnold, Nir Levine, Daniel J. Mankowitz +4

Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research a…

cs.LG2019

Challenges of Real-World Reinforcement Learning

Gabriel Dulac-Arnold, Daniel Mankowitz, Todd Hester

Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research a…