paper-with-me

Papers

Abstracted Trajectory Visualization for Explainability in Reinforcement Learning

2024-02-05 · Yoshiki Takagi, Roderick Tabalba, Nurit Kirshenbaum, Jason Leigh

Explainable AI (XAI) has demonstrated the potential to help reinforcement learning (RL) practitioners to understand how RL models work. However, XAI for users who do not have RL expertise (non-RL experts), has not been studied sufficiently. This results in a difficulty for the non-RL experts to participate in the fundamental discussion of how RL models should be designed for an incoming society where humans and AI coexist. Solving such a problem would enable RL experts to communicate with the non-RL experts in producing machine learning solutions that better fit our society. We argue that abstracted trajectories, that depicts transitions between the major states of the RL model, will be useful for non-RL experts to build a mental model of the agents. Our early results suggest that by leveraging a visualization of the abstracted trajectories, users without RL expertise are able to infer the behavior patterns of RL.

📄 PDF Abstract BibTeX arXiv:2402.07928

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Utilizing Explainability Techniques for Reinforcement Learning Model Assurance

2023-11-27 · Alexander Tapley, Kyle Gatesman, Luis Robaina, Brett Bissey 외

Explainable Reinforcement Learning (XRL) can provide transparency into the decision-making process of a Deep Reinforcement Learning (DRL) model and increase user trust and adoption in real-world use cases. By utilizing X…

Decision MakingDeep Reinforcement Learningmodelreinforcement-learning+1

A Closer Look at Reward Decomposition for High-Level Robotic Explanations

2023-04-25 · Wenhao Lu, Xufeng Zhao, Sven Magg, Martin Gromniak 외

Explaining the behaviour of intelligent agents learned by reinforcement learning (RL) to humans is challenging yet crucial due to their incomprehensible proprioceptive states, variational intermediate goals, and resultan…

Reinforcement Learning (RL)Vocal Bursts Intensity Prediction

Surrogate Fitness Metrics for Interpretable Reinforcement Learning

2025-04-20 · Philipp Altmann, Céline Davignon, Maximilian Zorn, Fabian Ritz 외

We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse policy demonstrations. A joint surrogate fitness function guides the optimization by combining local diver…

continuous-controlContinuous ControlDecision MakingDiversity+2

Explaining Deep Face Algorithms through Visualization: A Survey

2023-09-26 · Thrupthi Ann John, Vineeth N Balasubramanian, C. V. Jawahar

Although current deep models for face tasks surpass human performance on some benchmarks, we do not understand how they work. Thus, we cannot predict how it will react to novel inputs, resulting in catastrophic failures …

Survey

Learning from Explanations and Demonstrations: A Pilot Study

2020-11-01 · ACL (NL4XAI, INLG) 2020 11 · Silvia Tulli, Sebastian Wallkötter, Ana Paiva, Francisco S. Melo 외

AI has become prominent in a growing number of systems, and, as a direct consequence, the desire for explainability in such systems has become prominent as well. To build explainable systems, a large portion of existing …

text-to-speechText to SpeechTransfer Learning