Universal Knowledge-Seeking Agents for Stochastic Environments

By Laurent Orseau, Tor Lattimore, Marcus Hutter. 2013

42 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sergey Levine
2. Pieter Abbeel
3. Marc G. Bellemare
4. Yoshua Bengio
5. R´emi Munos
6. Yuxi Li
7. Chelsea Finn
8. Ruslan Salakhutdinov

In Computational Theory and Mathematics

1. Marc G. Bellemare
2. Tom Schaul
3. Georg Ostrovski
4. R´emi Munos
5. Shane Legg
6. Jan Leike
7. David Saxton
8. Geoffrey Irving

In Reinforcement Learning

1. Sergey Levine
2. Marc G. Bellemare
3. Pieter Abbeel
4. R´emi Munos
5. Yuxi Li
6. Georg Ostrovski
7. Tom Schaul
8. Shane Legg

Citations in the corpus

• Reward learning from human preferences and demonstrations in Atari (2018, background): “Reward-free learning attempts to avoid reward functions and instead use measures of intrinsic motivation, typically based on information theory, as a training signal (Chentanez et al., 2005; Schmidhuber, 2006; Orseau et al., 2013).”
• Unifying Count-Based Exploration and Intrinsic Motivation (2016, background): “Orseau et al. (2013) demonstrated that maximizing the sum of future information gains does lead to optimal behaviour, even though maximizing immediate information gain does not (Section 4).”