This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including theâ€¦ (More)

Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency isâ€¦ (More)

Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Caglar Gulcehre,â€¦ (More)

We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perceptionâ€¦ (More)

â€¢PUBLICATION TRACK More than hundred articles in peer-reviewed international journals and conference proceedings with 5300+ citations on Google Scholar (GS). My h-index is 40 as of 31/9/2018, and myâ€¦ (More)

Let k â‰¥ 3 be a fixed integer and let Z k (G) be the number of k-colourings of the graph G. For certain values of the average degree, the random variable Z k (G(n, m)) is known to be concentrated inâ€¦ (More)

Much of the recent work on phase transitions in discrete structures has been inspired by ingenious but non-rigorous approaches from physics. The physics predictions typically come in the form ofâ€¦ (More)

Diluted mean-field models are graphical models in which the geometry of interactions is determined by a sparse random graph or hypergraph. Based on a nonrigorous but analytic approach called the "â€¦ (More)