paper-with-me

홈 › Papers

Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning

2023-09-12 · Xiao Liu, Wubing Chen, Mao Tan

Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making problems. However, existing DRL agents make decisions in an opaque fashion, hindering the user from establishing trust and scrutinizing weaknesses of the agents. While recent research has developed Interpretable Policy Extraction (IPE) methods for explaining how an agent takes actions, their explanations are often inconsistent with the agent's behavior and thus, frequently fail to explain. To tackle this issue, we propose a novel method, Fidelity-Induced Policy Extraction (FIPE). Specifically, we start by analyzing the optimization mechanism of existing IPE methods, elaborating on the issue of ignoring consistency while increasing cumulative rewards. We then design a fidelity-induced mechanism by integrate a fidelity measurement into the reinforcement learning feedback. We conduct experiments in the complex control environment of StarCraft II, an arena typically avoided by current IPE methods. The experiment results demonstrate that FIPE outperforms the baselines in terms of interaction performance and consistency, meanwhile easy to understand.

📄 PDF Abstract BibTeX arXiv:2309.06097

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingDeep Reinforcement Learningreinforcement-learningReinforcement LearningSequential Decision MakingStarcraftStarcraft II

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Programmatic Policy Extraction by Iterative Local Search

2022-01-18 · Rasmus Larsen, Mikkel Nørgaard Schmidt

Reinforcement learning policies are often represented by neural networks, but programmatic policies are preferred in some cases because they are more interpretable, amenable to formal verification, or generalize better. …

reinforcement-learningReinforcement Learning (RL)

Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank

2026-04-07 · Xiangyong Chen, Xiaochuan Lin, Haoran Liu, Xuan Li 외 arxiv

Recent advances in reasoning-induced image quality assessment (IQA) have demonstrated the power of reinforcement learning to rank (RL2R) for training vision-language models (VLMs) to assess perceptual quality. However, e…

Image Quality AssessmentReinforcement Learning

Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models

2025-03-20 · Zhaoxin Li, Zhang Xi-Jia, Batuhan Altundas, Letian Chen 외

Semantic Interpretability in Reinforcement Learning (RL) enables transparency, accountability, and safer deployment by making the agent's decisions understandable and verifiable. Achieving this, however, requires a featu…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

SwarmThinkers: Learning Physically Consistent Atomic KMC Transitions at Scale

2025-05-26 · Qi Li, Kun Li, Haozhi Han, Honghui Shang 외

Can a scientific simulation system be physically consistent, interpretable by design, and scalable across regimes--all at once? Despite decades of progress, this trifecta remains elusive. Classical methods like Kinetic M…

Decision MakingGPU

Methodology for Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation

2024-04-03 · Joo Seung Lee, Malini Mahendra, Anil Aswani

Mechanical ventilation is a critical life support intervention that delivers controlled air and oxygen to a patient's lungs, assisting or replacing spontaneous breathing. While several data-driven approaches have been pr…

Off-policy evaluationreinforcement-learningReinforcement LearningReinforcement Learning (RL)