7 accepted papers
Nested Monte Carlo Search (NMCS) has numerous applications, ranging from chemical retrosynthesis to quantum circuit design. We propose a generalization of NMCS that we named Nested Depth Search (NDS), in which a fixed depth search is used during a higher-level playout to generate the states sent to
This paper introduces von Mises-Fisher exploration (vMF-exp), a scalable method for exploring large action sets in reinforcement learning problems where hyperspherical embedding vectors represent these actions. vMF-exp involves initially sampling a state embedding representation using a von Mises-Fi…
We are interested in realistic planning problems to model the behavior of Non-Playable Characters (NPCs) in video games. Search-based action planning, introduced by the game F.E.A.R. in 2005, has an exponential time complexity allowing to control only a dozen NPCs between two frames. A close study o…
Nested Rollout Policy Adaptation (NRPA) is an approach using online learning policies in a nested structure. It has achieved a great result in a variety of difficult combinatorial optimization problems. In this paper, we propose Meta-NRPA, which combines optimal stopping theory with NRPA for warm-st…
We define a new setting related to the evaluation of AND-OR directed acyclic graphs with partially ordered values. Such graphs arise naturally when solving games with incomplete information (e.g. most card games such as Bridge) or games with multiple criteria. In particular, this setting generalises…
Scheduling under uncertainty is an area of interest in artificial intelligence. We study the problem of Dynamic Controllability (DC) of Disjunctive Temporal Networks with Uncertainty (DTNU), which seeks a reactive scheduling strategy to satisfy temporal constraints in response to uncontrollable acti…
Learning-based methods are growing prominence for planning purposes. However, there are very few approaches for learning-assisted constrained path-planning on graphs, while there are multiple downstream practical applications. This is the case for constrained path-planning for Autonomous Unmanned Gr…