Aaron Keech

Reinforcement Learning · 2017

A researcher in the Science corpus: 1 paper; trusts 2 researchers and is trusted by 2 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 17 citations into it; #2,038 of 2,242 by trust here, #2,160 by citations

Whom Aaron Keech trusts overall

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

1. Christopher J. C. H. Watkins

Who trusts Aaron Keech overall

1. Eric

Papers from Aaron Keech's perspective

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

1. Playing Atari with Deep Reinforcement Learning (arXiv.org)
2. Apprenticeship learning via inverse reinforcement learning
3. Continuous Deep Q-Learning with Model-based Acceleration
4. A survey of robot learning from demonstration
5. Q-learning
6. Deep Reinforcement Learning from Human Preferences (Neural Information Processing Systems)
7. Control of Memory, Active Perception, and Action in Minecraft
8. The Malmo Platform for Artificial Intelligence Experimentation
9. Reinforcement Learning Via Practice and Critique Advice
10. Score-based Inverse Reinforcement Learning

Their papers

• Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds (2017) — 39 citations