Shawn Squire

Natural Language Processing · 2015

A researcher in the Science corpus: 2 papers; trusts 3 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Natural Language Processing — 16 citations into it
• Reinforcement Learning — 15 citations into it

Whom Shawn Squire trusts overall

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

1. Andrew Barto
2. Carlos Diuk

Papers from Shawn Squire's perspective

Ordered by how strongly the researchers Shawn Squire trusts endorse each paper. Same corpus, a different order for every researcher.

1. Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning
2. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper
3. Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation
4. Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density
5. Learning to Interpret Natural Language Navigation Instructions from Observations
6. Reinforcement Learning for Mapping Instructions to Actions
7. Building Portable Options: Skill Transfer in Reinforcement Learning
8. An object-oriented representation for efficient reinforcement learning
9. Q-learning
10. The Mathematics of Statistical Machine Translation: Parameter Estimation

Their papers

• Grounding English Commands to Reward Functions (2015) — 104 citations
• Portable Option Discovery for Automated Learning Transfer in Object-Oriented Markov Decision Processes (2015) — 34 citations