Alessio Pecorino

Reinforcement Learning · 2010–2013

A researcher in the Science corpus: 2 papers; trusts 4 researchers and is trusted by 3 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 9 citations into it; #1,843 of 2,242 by trust here, #1,750 by citations

Whom Alessio Pecorino trusts overall

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

1. Sham M. Kakade
2. Michail G. Lagoudakis

Who trusts Alessio Pecorino overall

1. Mohammad Ghavamzadeh
2. Pieter Abbeel
3. Yinlam Chow

Papers from Alessio Pecorino's perspective

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

1. Policy Gradient Methods for Reinforcement Learning with Function Approximation
2. Dynamic Programming and Markov Processes
3. Approximately Optimal Approximate Reinforcement Learning
4. A Natural Policy Gradient
5. Least-Squares Policy Iteration
6. On the sample complexity of reinforcement learning.
7. Error Bounds for Approximate Value Iteration
8. Approximate policy iteration: a survey and some new methods
9. Natural Actor-Critic
10. Dynamic policy programming

Their papers

• Safe Policy Iteration (2013) — 112 citations
• Fitted Policy Search: Direct Policy Search using a Batch Reinforcement Learning Approach (2010) — 5 citations