FlowPG: Action-constrained policy gradient with normalizing flows
Action-constrained reinforcement learning (ACRL) is a popular approach for solving safety-critical and resource-allocation related decision making problems. A major challenge in ACRL is to ensure agent taking a valid action satisfying constraints in each RL step. Commonly used approach of using a pr...
محفوظ في:
المؤلفون الرئيسيون: | BRAHMANAGE JANAKA CHATHURANGA THILAKARATHNA, LING, Jiajing, KUMAR, Akshat |
---|---|
التنسيق: | text |
اللغة: | English |
منشور في: |
Institutional Knowledge at Singapore Management University
2023
|
الموضوعات: | |
الوصول للمادة أونلاين: | https://ink.library.smu.edu.sg/sis_research/8551 https://ink.library.smu.edu.sg/context/sis_research/article/9554/viewcontent/11351_flowpg_action_constrained_poli.pdf |
الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
المؤسسة: | Singapore Management University |
اللغة: | English |
مواد مشابهة
-
Automata-guided control-flow-sensitive fuzz driver generation
بواسطة: ZHANG, Cen, وآخرون
منشور في: (2023) -
Sample-efficient iterative lower bound optimization of deep reactive policies for planning in continuous MDPs
بواسطة: LOW, Siow Meng, وآخرون
منشور في: (2022) -
Probabilistic Inference Based Message-Passing for Resource Constrained DCOPs
بواسطة: GHOSH, Supriyo, وآخرون
منشور في: (2015) -
Constrained multiagent reinforcement learning for large agent population
بواسطة: LING, Jiajing, وآخرون
منشور في: (2022) -
Towards gradient-based time-series explanations through a spatiotemporal attention network
بواسطة: LEE, Min Hun
منشور في: (2024)