H. van Seijen

Most-cited papers

Hybrid Reward Architecture for Reinforcement Learning
H. van Seijen, Mehdi Fatemi, Joshua Romoff, R. Laroche +2 more
2017Neural Information Processing Systems296 citations
Semantic Scholar
A theoretical and empirical analysis of Expected Sarsa
H. van Seijen, H. V. Hasselt, S. Whiteson, M. Wiering
2009IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning250 citations
Semantic Scholar
Systematic generalisation with group invariant predictions
Faruk Ahmed, Y. Bengio, H. van Seijen, Aaron C. Courville
2021International Conference on Learning Representations119 citations
Semantic Scholar
True Online Temporal-Difference Learning
H. van Seijen, A. Mahmood, P. Pilarski, Marlos C. Machado +1 more
2015Journal of machine learning research107 citations
Semantic Scholar
True Online TD(lambda)
H. van Seijen, R. Sutton
2014International Conference on Machine Learning68 citations
Semantic Scholar
A Deeper Look at Planning as Learning from Replay
H. van Seijen, R. Sutton
2015International Conference on Machine Learning61 citations
Semantic Scholar
True online TD(λ)
H. van Seijen, R. Sutton
2014International Conference on Machine Learning57 citations
Semantic Scholar
Modular Lifelong Reinforcement Learning via Neural Composition
Jorge Armando Mendez Mendez, H. van Seijen, Eric Eaton
2022International Conference on Learning Representations54 citations Open access
Semantic Scholar
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
H. van Seijen, Mehdi Fatemi, Arash Tavakoli
2019Neural Information Processing Systems35 citations
Semantic Scholar
Planning by Prioritized Sweeping with Small Backups
H. van Seijen, R. Sutton
2013International Conference on Machine Learning35 citations
Semantic Scholar
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni +7 more
2022arXiv.org27 citations Open access
Semantic Scholar
On Value Function Representation of Long Horizon Problems
Lucas Lehnert, R. Laroche, H. van Seijen
2018AAAI Conference on Artificial Intelligence26 citations Open access
Semantic Scholar
Multi-Advisor Reinforcement Learning
R. Laroche, Mehdi Fatemi, Joshua Romoff, H. van Seijen
2017arXiv.org25 citations
Semantic Scholar
Dead-ends and Secure Exploration in Reinforcement Learning
Mehdi Fatemi, Shikhar Sharma, H. van Seijen, Samira Ebrahimi Kahou
2019International Conference on Machine Learning22 citations
Semantic Scholar
Efficient planning in MDPs by small backups
H. van Seijen, R. Sutton
2013International Conference on Machine Learning19 citations
Semantic Scholar
Principled Offline RL in the Presence of Rich Exogenous Information
Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni +7 more
2022International Conference on Machine Learning18 citations
Semantic Scholar
Exploiting Best-Match Equations for Efficient Reinforcement Learning
H. van Seijen, S. Whiteson, H. V. Hasselt, M. Wiering
2011Journal of machine learning research18 citations
Semantic Scholar
EFFICIENT ABSTRACTION SELECTION IN REINFORCEMENT LEARNING
H. van Seijen, S. Whiteson, L. Kester
2013International Conference on Climate Informatics17 citations
Semantic Scholar
The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
H. van Seijen, Hadi Nekoei, Evan Racah, A. P. Sarath Chandar
2020Neural Information Processing Systems16 citations
Semantic Scholar
Effective Multi-step Temporal-Difference Learning for Non-Linear Function Approximation
H. van Seijen
2016arXiv.org16 citations
Semantic Scholar
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
Yi Wan, Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad +2 more
2022International Conference on Machine Learning15 citations Open access
Semantic Scholar
A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
Shangtong Zhang, R. Laroche, H. van Seijen, S. Whiteson +1 more
2020Adaptive Agents and Multi-Agent Systems15 citations
Semantic Scholar
Separation of Concerns in Reinforcement Learning
H. van Seijen, Mehdi Fatemi, Joshua Romoff, R. Laroche
201614 citations
Semantic Scholar
Learning Invariances for Policy Generalization
Rémi Tachet Des Combes, Philip Bachman, H. van Seijen
2018International Conference on Learning Representations12 citations
Semantic Scholar
Forward Actor-Critic for Nonlinear Function Approximation in Reinforcement Learning
Vivek Veeriah, H. van Seijen, R. Sutton
2017Adaptive Agents and Multi-Agent Systems10 citations
Semantic Scholar
E � cient Planning in MDPs by Small Backups
H. van Seijen, R. Sutton
201310 citations
Semantic Scholar
One-Shot Learning from a Demonstration with Hierarchical Latent Language
Nathaniel Weir, Xingdi Yuan, Marc-Alexandre Côté, Matthew J. Hausknecht +4 more
2022Adaptive Agents and Multi-Agent Systems8 citations Open access
Semantic Scholar
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
Sungryull Sohn, Sungtae Lee, Jongwook Choi, H. van Seijen +2 more
2021International Conference on Machine Learning8 citations
Semantic Scholar
Switching between different state representations in reinforcement learning
H. van Seijen, B. Bakker, L. Kester
20088 citations
Semantic Scholar
Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning
Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, H. van Seijen +1 more
2023CoLLAs6 citations
Semantic Scholar
Switching between Representations in Reinforcement Learning
H. van Seijen, S. Whiteson, L. Kester
2010Interactive Collaborative Information Systems6 citations
Semantic Scholar
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
Harry Zhao, Safa Alver, H. van Seijen, Romain Laroche +2 more
2023International Conference on Learning Representations5 citations
Semantic Scholar
Postponed Updates for Temporal-Difference Reinforcement Learning
H. van Seijen, S. Whiteson
20092009 Ninth International Conference on Intelligent Systems Design and Applications4 citations
Semantic Scholar
In reinforcement learning, all objective functions are not equal
R. Laroche, H. van Seijen
2018International Conference on Learning Representations3 citations
Semantic Scholar
Improving Scalability of Reinforcement Learning by Separation of Concerns
H. van Seijen, Mehdi Fatemi, Joshua Romoff, R. Laroche
2016arXiv.org3 citations
Semantic Scholar
Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning
H. van Seijen, H. V. Hasselt, S. Whiteson, M. Wiering
20093 citations
Semantic Scholar
Reinforcement Learning with Multiple, Qualitatively Different State Representations
H. van Seijen, B. Bakker, L. Kester
20072 citations
Semantic Scholar
Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning
Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, H. van Seijen +1 more
2023arXiv.org1 citations Open access
Semantic Scholar
An Empirical Evaluation of True Online TD(λ)
H. van Seijen, A. Mahmood, P. Pilarski, R. Sutton
2015arXiv.org1 citations
Semantic Scholar
An Empirical Evaluation of True Online TD({\lambda})
H. van Seijen, A. Mahmood, P. Pilarski, R. Sutton
20151 citations
Semantic Scholar
Coachable agents for interactive gameplay
R. Capobianco, H. van Seijen, Nolan Bard, Neil Burch +37 more
2026arXiv.org0 citations
Semantic Scholar
Combining Spatial and Temporal Abstraction in Planning for Better Generalization
Mingde Zhao, Safa Alver, H. van Seijen, Romain Laroche +2 more
2023arXiv.org0 citations Open access
Semantic Scholar
About the attractor phenomenon in decomposed reinforcement learning
R. Laroche, Mehdi Fatemi, Joshua Romoff, H. van Seijen
20180 citations
Semantic Scholar
Reinforcement learning under space and time constraints
H. van Seijen
20110 citations
Semantic Scholar
C ONSCIOUSNESS -I NSPIRED S PATIO -T EMPORAL A B - STRACTION FOR B ETTER G ENERALIZATION
Mingde Zhao, Safa Alver, H. van Seijen, Romain Laroche +2 more
0 citations
Semantic Scholar