… learning models (eg differentiable or tree-based models). In this work, we propose a deep reinforcementlearning … us to generate batches of counterfactual instances in a single forward …
… explanations to an AI agent's behavior [Miller [38]]. In this work, we focus on generating counterfactualexplanations for deep reinforcementlearning (… counterfactual state explanations, a …
… The latter aims at generating ex post explanations for … post-hoc explanations called counterfactualexplanations, which … from the predictive model, ie, counterfactual examples (CFs). …
… RELAX – the counterfactualexplanation technique based on a deep reinforcementlearning … Our method is modelagnostic: it can generate valid explanations for any model that are …
… counterfactuals to be explained; something that is known to be a powerful explanation mech… Our model generates counterfactualexplanations by comparing causal chains of the actual …
… whether counterfactualexplanations … counterfactualexplanations for RL agents by formulating the problem as a domain transfer problem which allows the use of adversarial learning …
… explanations of the behavior of deep reinforcementlearning (… indicates that the derived explanations are often unfalsifiable … approach grounded in counterfactual reasoning to test the …
… In this section, we describe RACCER, our approach for generating counterfactualexplanations for RL tasks. To generate a counterfactualexplanation x′, we require oracle access to …
Y Amitai, Y Septon, O Amir - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
… Counterfactual explanations are a form of contrastive explanations. A counterfactual explanation provides an answer to the question “Why p rather than q?”, where p is the fact which oc…