Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning
Jean-Bastien Grill · Michal Valko · Remi Munos

Tue Dec 6th 05:00 -- 05:20 PM @ Area 3

We study the sampling-based planning problem in Markov decision processes (MDPs) that we can access only through a generative model, usually referred to as Monte-Carlo planning. Our objective is to return a good estimate of the optimal value function at any state while minimizing the number of calls to the generative model, i.e. the sample complexity. We propose a new algorithm, TrailBlazer, able to handle MDPs with a finite or an infinite number of transitions from state-action to next states. TrailBlazer is an adaptive algorithm that exploits possible structures of the MDP by exploring only a subset of states reachable by following near-optimal policies. We provide bounds on its sample complexity that depend on a measure of the quantity of near-optimal states. The algorithm behavior can be considered as an extension of Monte-Carlo sampling (for estimating an expectation) to problems that alternate maximization (over actions) and expectation (over next states). Finally, another appealing feature of TrailBlazer is that it is simple to implement and computationally efficient.

Author Information

Jean-Bastien Grill (Inria Lille - Nord Europe)
Michal Valko (Inria Lille - Nord Europe)

Michal is a research scientist in DeepMind Paris and SequeL team at Inria Lille - Nord Europe, France, lead by Philippe Preux and Rémi Munos. He also teaches the course Graphs in Machine Learning at l'ENS Cachan. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. This means 1) reducing the “intelligence” that humans need to input into the system and 2) minimising the data that humans need spend inspecting, classifying, or “tuning” the algorithms. Another important feature of machine learning algorithms should be the ability to adapt to changing environments. That is why he is working in domains that are able to deal with minimal feedback, such as semi-supervised learning, bandit algorithms, and anomaly detection. The common thread of Michal's work has been adaptive graph-based learning and its application to the real world applications such as recommender systems, medical error detection, and face recognition. His industrial collaborators include Intel, Technicolor, and Microsoft Research. He received his PhD in 2011 from University of Pittsburgh under the supervision of Miloš Hauskrecht and after was a postdoc of Rémi Munos.

Remi Munos (Google DeepMind)

More from the Same Authors