Harm Van Seijen
11 papers · 2011–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π§ Keyword Pioneer π Cross-Pollinator (12) π Conference Polyglot (4) π Academic Marathon (13) π Interdisciplinary Bridge
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(15)
π§¬
Topic Evolution
π
Century Club
(11)
π
Conference Pioneer
π
Trend Setter
π₯
Unstoppable
(6)
Conferences
ICLR (3)
ICML (3)
NIPS (3)
JMLR (2)
Top co-authors
Keywords
value function
(4)
reinforcement learning
(4)
function approximation
(2)
model-based reinforcement learning
(2)
temporal-difference learning
(2)
policy optimization
(1)
model-based learning
(1)
discount factor
(1)
value estimation
(1)
q-value function
(1)
planning algorithm
(1)
eligibility trace
(1)
model-free learning
(1)
reward decomposition
(1)
inverse model
(1)
prioritized sweeping
(1)
dead-end state
(1)
secure exploration
(1)
bridge effect
(1)
exogenous information
(1)
Papers
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
ICLR 2024
Principled Offline RL in the Presence of Rich Exogenous Information
ICML 2023
Modular Lifelong Reinforcement Learning via Neural Composition
ICLR 2022
Systematic generalisation with group invariant predictions
ICLR 2021
The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
NIPS 2020
Dead-ends and Secure Exploration in Reinforcement Learning
ICML 2019
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
NIPS 2019
Hybrid Reward Architecture for Reinforcement Learning
NIPS 2017
True Online Temporal-Difference Learning
JMLR 2016
Planning by Prioritized Sweeping with Small Backups
ICML 2013
Exploiting Best-Match Equations for Efficient Reinforcement Learning
JMLR 2011