Search Results for author:
Found 5 papers, 0 papers with code
Learning safety critics via a non-contractive binary bellman operator
To that end, we study the properties of the binary safety critic associated with a deterministic dynamical system that seeks to avoid reaching an unsafe region.
Reinforcement Learning with Almost Sure Constraints
We argue that stationary policies are not sufficient for solving this problem, and that a rich class of policies can be found by endowing the controller with a scalar quantity, so called budget, that tracks how close the agent is to violating the constraint.
Learning to Act Safely with Limited Exposure and Almost Sure Certainty
Our analysis further highlights a trade-off between the time lag for the underlying MDP necessary to detect unsafe actions, and the level of exposure to unsafe events.
Assured RL: Reinforcement Learning with Almost Sure Constraints
We consider the problem of finding optimal policies for a Markov Decision Process with almost sure constraints on state transitions and action triplets.
Learning to be safe, in finite time
More precisely, by defining a handicap metric that counts the number of unsafe actions, we provide an algorithm for discarding unsafe machines (or actions), with probability one, that achieves constant handicap.
