Natalia Hernandez-Gardiol

Reinforcement Learning · 2000–2002

A researcher in the Science corpus: 2 papers; trusts 3 researchers and is trusted by 2 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 5 citations into it

Whom Natalia Hernandez-Gardiol trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Andrew McCallum
2. John N. Tsitsiklis
3. Stephen H. Muggleton
4. David Chapman
5. Ronald J. Williams
6. Leslie Pack Kaelbling
7. Nicolas Meuleau
8. Dana H. Ballard
9. Richard S. Sutton

Who trusts Natalia Hernandez-Gardiol overall

1. Bernhard Hengst
2. Andrew Barto
3. Sridhar Mahadevan
4. Balaraman Ravindran

Papers from Natalia Hernandez-Gardiol's perspective

Ordered by how strongly the researchers Natalia Hernandez-Gardiol trusts endorse each paper. Same corpus, a different order for every researcher.

1. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
2. Reinforcement learning with selective perception and hidden state
3. Inductive Logic Programming: Theory and Methods
4. Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems
5. An Analysis of Temporal-Difference Learning with Function Approximation
6. Learning Finite-State Controllers for Partially Observable Environments
7. Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons
8. An Analysis of Temporal-Di erence Learning with Function Approximation
9. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
10. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)

Their papers

• The Thing that we Tried Didn't Work very Well: Deictic Representation in Reinforcement Learning (2002) — 42 citations
• Hierarchical Memory-Based Reinforcement Learning (2000) — 65 citations