The 2014 international planning competition: Progress and trends

M Vallati, L Chrpa, M Grześ, TL McCluskey, M Roberts… - Ai Magazine, 2015 - ojs.aaai.org
Abstract We review the 2014 International Planning Competition (IPC-2014), the eighth in a
series of competitions starting in 1998. IPC-2014 was held in three separate parts to assess …

Goal probability analysis in probabilistic planning: Exploring and enhancing the state of the art

M Steinmetz, J Hoffmann, O Buffet - Journal of Artificial Intelligence …, 2016 - jair.org
Unavoidable dead-ends are common in many probabilistic planning problems, eg when
actions may fail or when operating under resource constraints. An important objective in …

Non-stationary Markov decision processes, a worst-case approach using model-based reinforcement learning

E Lecarpentier, E Rachelson - Advances in neural …, 2019 - proceedings.neurips.cc
This work tackles the problem of robust zero-shot planning in non-stationary stochastic
environments. We study Markov Decision Processes (MDPs) evolving over time and …

On monte carlo tree search and reinforcement learning

T Vodopivec, S Samothrakis, B Ster - Journal of Artificial Intelligence …, 2017 - jair.org
Fuelled by successes in Computer Go, Monte Carlo tree search (MCTS) has achieved wide-
spread adoption within the games community. Its links to traditional reinforcement learning …

Safe path planning for UAV urban operation under GNSS signal occlusion risk

JA Delamer, Y Watanabe, CPC Chanel - Robotics and Autonomous …, 2021 - Elsevier
This paper introduces a concept of safe path planning for UAV's autonomous operation in an
urban environment where GNSS-positioning may become unreliable or even unavailable. If …

[PDF][PDF] A framework for reinforcement learning and planning

TM Moerland, J Broekens… - arxiv preprint …, 2020 - icaps20subpages.icaps-conference …
Two successful approaches to Markov Decision Process optimization are planning and
reinforcement learning. Both research communities operate large separate. This framework …

Nonlinear Hybrid Planning with deep net ltearned transition models and mixed-integer linear programming

B Say, G Wu, YQ Zhou… - … Joint Conference on …, 2017 - research.monash.edu
In many real-world hybrid (mixed discrete continuous) planning problems such as Reservoir
Control, Heating, Ventilation and Air Conditioning (HVAC), and Navigation, it is difficult to …

Learning to design without prior data: Discovering generalizable design strategies using deep learning and tree search

A Raina, J Cagan, C McComb - Journal of …, 2023 - asmedigitalcollection.asme.org
Abstract Building an Artificial Intelligence (AI) agent that can design on its own has been a
goal since the 1980s. Recently, deep learning has shown the ability to learn from large …

[BOOK][B] Autonomous horizons: the way forward

GL Zacharias - 2019 - apps.dtic.mil
Dr. Greg Zacharias, Chief Scientist of the United States Air Force 2015-18, explores next
steps in autonomous systems AS development, fielding, and training. Rapid advances in AS …

[BOOK][B] Handbuch der künstlichen Intelligenz

G Görz, CR Rollinger, J Schneeberger - 2003 - degruyter.com
Liste der Autoren Page 1 Liste der Autoren Clemens Beckstein Gerhard Brewka Christian
Borgelt Wolfram Burgard Hans-Dieter Burkhard Stephan Busemann Thomas Christaller Leonie …