Clustered Policy Decision Ranking
Policies trained via reinforcement learning (RL) are often very complex even for simple tasks. In an episode with n time steps, a policy will make n decisions on actions to take, many of which may appear non-intuitive to the observer. Moreover, it is not clear which of these decisions directly contribute towards achieving the reward and how significant their contribution is. Given a trained policy, we propose a black-box method based on statistical covariance estimation that clusters the states of the environment and ranks each cluster according to the importance of decisions made in its states. We compare our measure against a previous statistical fault localization based ranking procedure.
Code (0)
등록된 구현이 없습니다.
Tasks
Fault localizationReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Reinforcement Learning with Heterogeneous Data: Estimation and Inference
Reinforcement Learning (RL) has the promise of providing data-driven support for decision-making in a wide range of problems in healthcare, education, business, and other domains. Classical RL methods focus on the mean o…
Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)Ranking Policy Decisions
Policies trained via Reinforcement Learning (RL) are often needlessly complex, making them difficult to analyse and interpret. In a run with $n$ time steps, a policy will make $n$ decisions on actions to take; we conject…
Atari GamesReinforcement Learning (RL)Causal policy ranking
Policies trained via reinforcement learning (RL) are often very complex even for simple tasks. In an episode with $n$ time steps, a policy will make $n$ decisions on actions to take, many of which may appear non-intuitiv…
counterfactualCounterfactual ReasoningReinforcement Learning (RL)Reinforcement Learning to Rank in E-Commerce Search Engine: Formalization, Analysis, and Application
In e-commerce platforms such as Amazon and TaoBao, ranking items in a search session is a typical multi-step decision-making problem. Learning to rank (LTR) methods have been widely applied to ranking problems. However, …
Decision MakingLearning-To-RankReinforcement LearningReinforcement Learning (RL)$\text{DT}^2$: Decision-Targeted Digital Twins
A digital twin (DT) is a virtual model of a real-world system that can assist decision-making by simulating scenarios induced by different policies. However, typical machine learning-based DTs do not optimise for this us…