Representing, enforcing, or evaluating safety, resource, and risk requirements in reinforcement-learning behavior.
Tagged articles
14 articles in this tag.
Your agent keeps taking an action you already know is wrong. You add a shield. Now you cannot tell whether it is helping or quietly starving the learner.
Read tutorial
A shield that rejects unsafe actions every run can still support no safety claim at all.
Read tutorial
A hand-picked penalty weight can look fine in one run and drift over budget in the next. The weight was never told what the budget is — so it can't respect…
Read tutorial
You write down the problem cleanly: maximize expected reward, keep expected cost under a budget. Then you freeze, because there is no obvious place to put…
Read tutorial
A penalty is a price. A constraint is a wall. Most RL safety problems fail because practitioners build walls out of prices and then act surprised when the…
Read tutorial
Two policies. Same expected return. One of them occasionally produces an episode so bad you would never deploy it. The mean cannot tell them apart — not…
Read tutorial
You have the checklist memorized. State size. Data cost. Observability. Action structure. Baselines. Debugging burden. Then a real project lands on your…
Read tutorial
Two actions can offer the same expected return and still feel completely different to the agent that takes them. One delivers a steady, predictable…
Read tutorial
Your agent keeps walking into walls. It selects skills still on cooldown, tries to buy items it cannot afford, and bumps against the grid edge like a moth…
Read tutorial
Two policies. One wins on average. The other wins on the days you actually have to survive. If your selection rule can't tell them apart, you're not…
Read tutorial
Two policies can share the exact same expected return and still feel completely different to the person who has to live with the outcomes. One delivers…
Read tutorial
Your agent proposes an action that crosses a hard safety boundary. You can block it, replace it, or fall back to a known-safe controller. The naive…
Read tutorial
A higher estimated value is not proof of improvement. It is a hypothesis about actions the dataset may never have supported.
Read tutorial
Two agents start on the same grid. Same states, same actions, same rewards, same exploration schedule. One hugs the edge of a cliff and occasionally falls.…
Read tutorial