1 code implementation • 9 Jun 2023 • Jonathon Schwartz, Hanna Kurniawati, Marcus Hutter
The design of autonomous agents that can interact effectively with other agents without prior coordination is a core problem in multi-agent systems.
1 code implementation • 14 May 2023 • Marcus Hoerger, Hanna Kurniawati, Dirk Kroese, Nan Ye
At each planning step, our method uses a novel lazy Cross-Entropy method to search the space of policy trees, which provide a simple policy representation.
1 code implementation • 21 Feb 2023 • Marcus Hoerger, Hanna Kurniawati, Dirk Kroese, Nan Ye
ADVT uses the estimated diameters of the cells to form an upper-confidence bound on the action value function within the cell, guiding the Monte Carlo Tree Search expansion and further discretization of the action space.
1 code implementation • 13 Sep 2022 • Marcus Hoerger, Hanna Kurniawati, Dirk Kroese, Nan Ye
A Voronoi tree is a Binary Space Partitioning (BSP) that implicitly maintains the partition of a cell as the Voronoi diagram of two points sampled from the cell.
no code implementations • 2 Apr 2021 • Jimy Cai Huang, Hanna Kurniawati
This paper proposes a mechanism to assess the safety of autonomous cars.
no code implementations • 4 Nov 2020 • Marcus Hoerger, Hanna Kurniawati
Most on-line solvers rely on discretising the observation space or artificially limiting the number of observations that are considered during planning to compute tractable policies.
no code implementations • 9 Jul 2019 • Nicholas Collins, Hanna Kurniawati
We propose a neural network architecture, called TransNet, that combines planning and model learning for solving Partially Observable Markov Decision Processes (POMDPs) with non-uniform system dynamics.
no code implementations • 15 May 2019 • Jonathon Schwartz, Hanna Kurniawati
Further work is needed in developing scalable RL algorithms and testing these algorithms in larger and higher fidelity environments.
no code implementations • 27 Nov 2015 • Dimitri Klimenko, Hanna Kurniawati, Marcus Gallagher
In this paper, we formalize the process of classical search as a metalevel decision problem, the Abstract Search MDP.
no code implementations • 12 May 2014 • Georgios Papadopoulos, Hanna Kurniawati, Nicholas M. Patrikalakis
The purpose of this paper is to show that asymptotically optimal motion planning for dynamical systems with differential constraints can be achieved without the use of a steering function.
Robotics