Peter Henderson

An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning

How do we formalize the challenge of credit assignment in reinforcement ...
03/10/2021 ∙ by Dilip Arumugam, et al. ∙ 0 ∙ share

read it
With Little Power Comes Great Responsibility

Despite its importance to experimental design, statistical power (the pr...
10/13/2020 ∙ by Dallas Card, et al. ∙ 5 ∙ share

read it
Ideas for Improving the Field of Machine Learning: Summarizing Discussion from the NeurIPS 2019 Retrospectives Workshop

This report documents ideas for improving the field of machine learning,...
07/21/2020 ∙ by Shagun Sodhani, et al. ∙ 44 ∙ share

read it
TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?

We investigate whether Jacobi preconditioning, accounting for the bootst...
07/06/2020 ∙ by Joshua Romoff, et al. ∙ 0 ∙ share

read it
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

With the recent wave of progress in artificial intelligence (AI) has com...
04/15/2020 ∙ by Miles Brundage, et al. ∙ 0 ∙ share

read it
Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning

Accurate reporting of energy and carbon usage is essential for understan...
01/31/2020 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
Separating value functions across time-scales

In many finite horizon episodic reinforcement learning (RL) settings, it...
02/05/2019 ∙ by Joshua Romoff, et al. ∙ 0 ∙ share

read it
Distilling Information from a Flood: A Possibility for the Use of Meta-Analysis and Systematic Review in Machine Learning Research

The current flood of information in all areas of machine learning resear...
12/03/2018 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
An Introduction to Deep Reinforcement Learning

Deep reinforcement learning is the combination of reinforcement learning...
11/30/2018 ∙ by Vincent Francois-Lavet, et al. ∙ 28 ∙ share

read it
The RLLChatbot: a solution to the ConvAI Challenge

Current conversational systems can follow simple commands and answer bas...
11/07/2018 ∙ by Nicolas A. Gontier, et al. ∙ 0 ∙ share

read it
Adversarial Gain

Adversarial examples can be defined as inputs to a model which induce a ...
11/04/2018 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods

Recent analyses of certain gradient descent optimization methods have sh...
10/05/2018 ∙ by Peter Henderson, et al. ∙ 12 ∙ share

read it
Reward Estimation for Variance Reduction in Deep Reinforcement Learning

In reinforcement learning (RL), stochastic environments can make learnin...
05/09/2018 ∙ by Joshua Romoff, et al. ∙ 0 ∙ share

read it
Learning Robust Dialog Policies in Noisy Environments

Modern virtual personal assistants provide a convenient interface for co...
12/11/2017 ∙ by Maryam Fazel-Zarandi, et al. ∙ 0 ∙ share

read it
Ethical Challenges in Data-Driven Dialogue Systems

The use of dialogue systems as a medium for human-machine interaction is...
11/24/2017 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
Underwater Multi-Robot Convoying using Visual Tracking by Detection

We present a robust multi-robot convoying approach that relies on visual...
09/25/2017 ∙ by Florian Shkurti, et al. ∙ 0 ∙ share

read it
Cost Adaptation for Robust Decentralized Swarm Behaviour

The multi-agent swarm system is a robust paradigm which can drive effici...
09/21/2017 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
Deep Reinforcement Learning that Matters

In recent years, significant progress has been made in solving challengi...
09/19/2017 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
Benchmark Environments for Multitask Learning in Continuous Domains

As demand drives systems to generalize to various domains and problems, ...
08/14/2017 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
A Survey of Available Corpora for Building Data-Driven Dialogue Systems

During the past decade, several areas of speech and language understandi...
12/17/2015 ∙ by Iulian Vlad Serban, et al. ∙ 0 ∙ share

read it

Peter Henderson

Featured Co-authors

Yoshua Bengio

Joelle Pineau

Doina Precup

Emma Brunskill

Adrian Weller

Dan Jurafsky

Marc G. Bellemare

Junaed Sattar

Laurent Charlin

Yann Ollivier

David Meger

An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning

With Little Power Comes Great Responsibility

Ideas for Improving the Field of Machine Learning: Summarizing Discussion from the NeurIPS 2019 Retrospectives Workshop

TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning

Separating value functions across time-scales

Distilling Information from a Flood: A Possibility for the Use of Meta-Analysis and Systematic Review in Machine Learning Research

An Introduction to Deep Reinforcement Learning

The RLLChatbot: a solution to the ConvAI Challenge

Adversarial Gain

Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods

Reward Estimation for Variance Reduction in Deep Reinforcement Learning

Learning Robust Dialog Policies in Noisy Environments

Ethical Challenges in Data-Driven Dialogue Systems

Underwater Multi-Robot Convoying using Visual Tracking by Detection

Cost Adaptation for Robust Decentralized Swarm Behaviour

Deep Reinforcement Learning that Matters

Benchmark Environments for Multitask Learning in Continuous Domains

A Survey of Available Corpora for Building Data-Driven Dialogue Systems