Picture for Agustin Castellano

Agustin Castellano

Learning safety critics via a non-contractive binary bellman operator

Jan 23, 2024
Viaarxiv icon

Reinforcement Learning with Almost Sure Constraints

Dec 09, 2021
Figure 1 for Reinforcement Learning with Almost Sure Constraints
Figure 2 for Reinforcement Learning with Almost Sure Constraints
Figure 3 for Reinforcement Learning with Almost Sure Constraints
Viaarxiv icon

Learning to Act Safely with Limited Exposure and Almost Sure Certainty

May 25, 2021
Figure 1 for Learning to Act Safely with Limited Exposure and Almost Sure Certainty
Figure 2 for Learning to Act Safely with Limited Exposure and Almost Sure Certainty
Figure 3 for Learning to Act Safely with Limited Exposure and Almost Sure Certainty
Figure 4 for Learning to Act Safely with Limited Exposure and Almost Sure Certainty
Viaarxiv icon

Assured RL: Reinforcement Learning with Almost Sure Constraints

Dec 24, 2020
Figure 1 for Assured RL: Reinforcement Learning with Almost Sure Constraints
Figure 2 for Assured RL: Reinforcement Learning with Almost Sure Constraints
Viaarxiv icon

Learning to be safe, in finite time

Oct 01, 2020
Figure 1 for Learning to be safe, in finite time
Figure 2 for Learning to be safe, in finite time
Figure 3 for Learning to be safe, in finite time
Figure 4 for Learning to be safe, in finite time
Viaarxiv icon