Joseph Modayil

发表

Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction

Patrick M. Pilarski, Doina Precup, Richard S. Sutton, 2011, AAMAS.

Rainbow: Combining Improvements in Deep Reinforcement Learning

Tom Schaul, David Silver, Matteo Hessel, 2017, AAAI.

Vector-based navigation using grid-like representations in artificial agents

Razvan Pascanu, Raia Hadsell, Fabio Viola, 2018, Nature.

Surprise and Curiosity for Big Data Robotics

R. Sutton, Joseph Modayil, Adam White, 2014 .

Building Machines that Learn and Think for Themselves: Commentary on Lake et al., Behavioral and Brain Sciences, 2017

Tom Schaul, Nando de Freitas, Shane Legg, 2017, 1711.08378.

Multi-timescale nexting in a reinforcement learning robot

Richard S. Sutton, Adam White, Joseph Modayil, 2011, Adapt. Behav..

Scaling-up Knowledge for a Cognizant Robot

Thomas Degris, Joseph Modayil, Joseph Modayil, 2012, AAAI Spring Symposium: Designing Intelligent Robots.

Exploiting Local Perceptual Models for Topological Map-Building

Joseph Modayil, M. MacMahon, P. Beeson, 2003 .

Off-Policy Knowledge Maintenance for Robots

R. Sutton, Joseph Modayil, T. Degris, 2010 .

Towards Bootstrap Learning for Object Discovery ∗

Joseph Modayil, B. Kuipers, 2004 .

A Collaborative Approach to the Simultaneous Multi-joint Control of a Prosthetic Arm

Patrick M. Pilarski, Craig Sherstan, Joseph Modayil, 2015, 2015 IEEE International Conference on Rehabilitation Robotics (ICORR).

Discovering sensor space: Constructing spatial embeddings that explain sensor correlations

Joseph Modayil, Joseph Modayil, 2010, 2010 IEEE 9th International Conference on Development and Learning.

Prediction Driven Behavior: Learning Predictions that Drive Fixed Responses

Richard S. Sutton, Joseph Modayil, R. Sutton, 2014, AAAI 2014.

Multi-timescale Nexting in a Reinforcement Learning Robot

Richard S. Sutton, Adam White, Joseph Modayil, 2012, SAB.

Acquiring Diverse Predictive Knowledge in Real Time by Temporal-difference Learning

R. Sutton, Joseph Modayil, P. Pilarski, 2012 .

AAAI Workshop - Technical Report: Preface

Doina Precup, Joseph Modayil, Satinder Singh, 2011, AAAI 2011.

Assessing Human Interaction in Virtual Reality With Continually Learning Prediction Agents Based on Reinforcement Learning Algorithms: A Pilot Study

Adam S. R. Parker, Michael Bradley Johanson, Dylan J. A. Brenneis, 2021, ArXiv.

Ray Interference: a Source of Plateaus in Deep Reinforcement Learning pdf

Razvan Pascanu, Tom Schaul, Joseph Modayil, 2019, ArXiv.

Factoring the Mapping Problem: Mobile Robot Map-building in the Hybrid Spatial Semantic Hierarchy

Benjamin Kuipers, Patrick Beeson, Joseph Modayil, 2010, Int. J. Robotics Res..

The Frost Hollow Experiments: Pavlovian Signalling as a Path to Coordination and Communication Between Agents

Adam S. R. Parker, Michael Bradley Johanson, Dylan J. A. Brenneis, 2022, ArXiv.

Pavlovian Signalling with General Value Functions in Agent-Agent Temporal Decision Making pdf

Patrick M. Pilarski, Elnaz Davoodi, Adam White, 2022, ArXiv.

Robot developmental learning of an object ontology grounded in sensorimotor experience

Benjamin Kuipers, Joseph Modayil, Joseph Modayil, 2007 .

Deep Reinforcement Learning and the Deadly Triad pdf

Matteo Hessel, Florian Strub, Joseph Modayil, 2018, ArXiv.

Loss of Plasticity in Continual Deep Reinforcement Learning

Marlos C. Machado, Joseph Modayil, Adam White, 2023, ArXiv.

Integrating Sensing and Cueing for More Effective Activity Reminders

Henry A. Kautz, Craig Harman, Joseph Modayil, 2008, AAAI Fall Symposium: AI in Eldercare: New Solutions to Old Problems.

Local metrical and global topological maps in the hybrid spatial semantic hierarchy

Benjamin Kuipers, Patrick Beeson, Matt MacMahon, 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

Integrating Multiple Representations of Spatial Knowledge for Mapping, Navigation, and Communication

Benjamin Kuipers, Patrick Beeson, Matt MacMahon, 2007, Interaction Challenges for Intelligent Assistants.

Learning Grounded Communicative Intent from Human-Robot Dialog

Joseph Modayil, Joseph Modayil, 2010, AAAI Fall Symposium: Dialog with Robots.

Autonomous Development of a Grounded Object Ontology by a Learning Robot

Benjamin Kuipers, Joseph Modayil, Joseph Modayil, 2007, AAAI.

On Inductive Biases in Deep Reinforcement Learning pdf

David Silver, Matteo Hessel, Joseph Modayil, 2019, ArXiv.

Learning to Look by Self-Prediction

R. Hadsell, Joseph Modayil, M. Grimes, 2023, Trans. Mach. Learn. Res..

Scaling life-long off-policy learning

Richard S. Sutton, Adam White, Joseph Modayil, 2012, 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL).

Research Statement

Joseph Modayil, 2006 .

Universal Option Models

Shalabh Bhatnagar, Richard S. Sutton, Csaba Szepesvári, 2014, NIPS.

Two Perspectives on Learning Rich Representations from Robot Experience

Joseph Modayil, Joseph Modayil, 2013, AAAI Workshop: Learning Rich Representations from Low-Level Sensors.

Acquiring a broad range of empirical knowledge in real time by temporal-difference learning

Patrick M. Pilarski, Richard S. Sutton, Adam White, 2012, 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

Multi-timescale nexting in a reinforcement learning robot

R. Sutton, Joseph Modayil, Adam White, 2011, Adapt. Behav..

Acquiring Diverse Predictive Knowledge in Real Time by Temporal-difference Learning

R. Sutton, Joseph Modayil, P. Pilarski, 2012 .

Bootstrap learning of foundational representations

Benjamin Kuipers, Patrick Beeson, Joseph Modayil, 2006, Connect. Sci..

Adapting the Function Approximation Architecture in Online Reinforcement Learning pdf

Joseph Modayil, John D. Martin, Joseph Modayil, 2021, ArXiv.

Natural Value Approximators: Learning when to Trust Past Estimates

Tom Schaul, David Silver, Zhongwen Xu, 2017, NIPS.

Improving the recognition of interleaved activities

Henry A. Kautz, Tongxin Bai, Joseph Modayil, 2008, UbiComp.

Multi-timescale nexting in a reinforcement learning robot

R. Sutton, Joseph Modayil, Adam White, 2011, Adapt. Behav..

Towards model-free RL algorithms that scale well with unstructured data

Joseph Modayil, Zaheer Abbas, 2023, ArXiv.

Predicting the near-future impact of daily activities on heart rate for at-risk populations

Joseph Modayil, Gordana Velikic, Mark Bocko, 2011, 2011 IEEE 13th International Conference on e-Health Networking, Applications and Services.

The initial development of object knowledge by a learning robot

Benjamin Kuipers, Joseph Modayil, Joseph Modayil, 2008, Robotics Auton. Syst..

Vector-based navigation using grid-like representations in artificial agents

Neil C. Rabinowitz, T. Lillicrap, K. Kavukcuoglu, 2018, Nature.