Harm van Seijen

Identifiers

• name variant Harm van Seijen 0.60 · backfill

Papers (7)

1. Hybrid Reward Architecture for Reinforcement Learning cs.LG · 2017 · author #1
2. Multi-Advisor Reinforcement Learning cs.LG · 2017 · author #4
3. Separation of Concerns in Reinforcement Learning cs.LG · 2016 · author #1
4. Effective Multi-step Temporal-Difference Learning for Non-Linear Function Approximation cs.AI · 2016 · author #1
5. True Online Temporal-Difference Learning cs.AI · 2015 · author #1
6. An Empirical Evaluation of True Online TD({\lambda}) cs.AI · 2015 · author #1
7. Planning by Prioritized Sweeping with Small Backups cs.AI · 2013 · author #1

Mentions

• 1507.00353 #1 · backfill · confidence 0.70 Harm van Seijen
• 1301.2343 #1 · backfill · confidence 0.70 Harm van Seijen

Frequent Coauthors

• Joshua Romoff 3 shared papers
• Mehdi Fatemi 3 shared papers
• Richard S. Sutton 3 shared papers
• Romain Laroche 3 shared papers
• A. Rupam Mahmood 2 shared papers
• Patrick M. Pilarski 2 shared papers
• Jeffrey Tsang 1 shared papers
• Marlos C. Machado 1 shared papers
• Tavian Barnes 1 shared papers