Picture for Hanna Krasowski

Hanna Krasowski

Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking

Add code
Jun 06, 2024
Viaarxiv icon

Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea

Add code
Feb 13, 2024
Viaarxiv icon

Maximizing Seaweed Growth on Autonomous Farms: A Dynamic Programming Approach for Underactuated Systems Navigating on Uncertain Ocean Currents

Add code
Jul 04, 2023
Viaarxiv icon

Stranding Risk for Underactuated Vessels in Complex Ocean Currents: Analysis and Controllers

Add code
Jul 04, 2023
Viaarxiv icon

Verifiably Safe Reinforcement Learning with Probabilistic Guarantees via Temporal Logic

Add code
Dec 12, 2022
Viaarxiv icon

Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes

Add code
Oct 19, 2022
Figure 1 for Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes
Figure 2 for Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes
Figure 3 for Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes
Figure 4 for Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes
Viaarxiv icon

Provably Safe Reinforcement Learning: A Theoretical and Experimental Comparison

Add code
May 13, 2022
Figure 1 for Provably Safe Reinforcement Learning: A Theoretical and Experimental Comparison
Figure 2 for Provably Safe Reinforcement Learning: A Theoretical and Experimental Comparison
Figure 3 for Provably Safe Reinforcement Learning: A Theoretical and Experimental Comparison
Figure 4 for Provably Safe Reinforcement Learning: A Theoretical and Experimental Comparison
Viaarxiv icon