Publications

Niklas Paulig, and Ostap Okhrin. Robust path following on rivers using bootstrapped reinforcement learning. Ocean engineering, (298)Elsevier Science B.V., Apr 15, 2024. [PUMA: FIS_scads Path waterways Autonomous Restricted learning, surface vessel, reinforcement Deep topic_engineering following,]

Martin Waltz, and Ostap Okhrin. Spatial–temporal recurrent reinforcement learning for autonomous ships. Neural Networks, (2023)165:634--653, Elsevier Science B.V., Jun 15, 2023. [PUMA: FIS_scads Networks, Autonomous surface Computer, Recurrency, Deep vehicle, COLREG, learning, Algorithms, Psychology, Ships, Reward reinforcement topic_engineering Neural Reinforcement,]

Fabian Hart, Martin Waltz, and Ostap Okhrin. Two-step dynamic obstacle avoidance. Knowledge-based systems, (302)Elsevier Science B.V., Oct 25, 2024. [PUMA: FIS_scads Dynamic Local learning Deep Supervised planning, path learning, avoidance, reinforcement topic_engineering obstacle]