Janusz Marecki

Reinforcement Learning · 2008–2017

A researcher in the Science corpus: 4 papers; trusts 3 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

Whom Janusz Marecki trusts overall

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

  1. Vincent Conitzer
  2. Michael L. Littman
  3. Julien Pérolat
  4. Michael P. Wellman
  5. Tuomas Sandholm

Who trusts Janusz Marecki overall

  1. Frans Adriaan Oliehoek
  2. Christopher Kiekintveld
  3. Bo Li
  4. Milind Tambe
  5. Dmytro Korzhyk
  6. Jakob N. Foerster

Papers from Janusz Marecki's perspective

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

  1. Markov Games as a Framework for Multi-Agent Reinforcement Learning
  2. Human-level control through deep reinforcement learning
  3. Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm
  4. Mastering the game of Go with deep neural networks and tree search
  5. Correlated Q-Learning
  6. Fast algorithms for finding randomized strategies in game trees
  7. Friend-or-Foe Q-learning in General-Sum Games
  8. A Neural Substrate of Prediction and Reward
  9. The evolution of cooperation
  10. If multi-agent learning is the answer, what is the question?

Their papers