Computationally Efficient Safe Reinforcement Learning for Power Systems

Tabas, Daniel; Zhang, Baosen

doi:10.23919/acc53348.2022.9867652

Cited by 11 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ketika Tabas dan Raduan melihat dampak orientasi pasar terhadap kinerja bisnis, mereka menemukan bahwa hal tersebut memperbaiki keadaan. Kinerja suatu perusahaan meningkat sebanding dengan seberapa berorientasi pasar pengembangan produk dan proses produksinya, menurut penelitian mereka (Tabas & Zhang, 2022) (Raduan et al, 2009). Namun, Au dan Tse menemukan bahwa tidak ada hubungan atau tidak ada hubungan di antara kinerja perusahaan dengan orientasi pasar (Raduan et al, 2009).…”

Section: Tabel 2 Definisi Umk Berdasarkan Standar Bank Duniaunclassified

Pengaruh strategi inovasi dan orientasi pasar terhadap keunggulan bersaing dan kinerja perusahaan (studi pada UKM OKE OCE Jakarta)

Mulyono

2024

Journal of Economics, Business, Accounting and Management

View full text Add to dashboard Cite

The DKI Jakarta Provincial Government program, OK OCE (One District, One Entrepreneurship Center), was pioneered by Anies Baswedan and Sandiaga Uno. The aim is to assist micro, small and medium enterprises (MSMEs) in cultivating an entrepreneurial spirit through the Cooperatives and MSMEs Sub-Department. The main objective of this program is to realize an economic mission that prioritizes society, justice, prosperity, quality and broad insight. This research aims to show and analyze three ways in which innovation strategy and market orientation influence the performance of OK OCE SME companies in Jakarta: through competitive advantage, directly and indirectly, through innovation strategy and market orientation. All SMEs partnering with OK OCE in Jakarta are research subjects. Data were analyzed using SEM-PLS. The total research sample was 100 small and medium business owners in OK OCE Jakarta, and the simple random sampling method was used for probability sampling. Based on the findings of this research, (1) Although innovation strategies SMEs in OK OCE Jakarta gain a competitive advantage, this does not directly improve their performance; (2) The increase in the performance of SMEs in OK OCE Jakarta is not a direct result of market orientation, but rather the result of competitive advantage. 3 The increase in the performance of SMEs in OK OCE Jakarta is significantly influenced by innovation strategy and market orientation.

show abstract

Section: Tabel 2 Definisi Umk Berdasarkan Standar Bank Duniaunclassified

Pengaruh strategi inovasi dan orientasi pasar terhadap keunggulan bersaing dan kinerja perusahaan (studi pada UKM OKE OCE Jakarta)

Mulyono

2024

Journal of Economics, Business, Accounting and Management

View full text Add to dashboard Cite

show abstract

“…In this article, we present an action masking approach, for which the agent can only choose actions that are verified as safe. Most research on action masking considers discrete action spaces; common applications are autonomous driving [45]- [50] and power systems [51]. Usually, the action verification is tailored to the specific application and, thus, cannot be directly transferred to other applications.…”

Section: B) Motion Planning For Vesselsmentioning

confidence: 99%

Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea

Krasowski,

Althoff

2024

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

For safe operation, autonomous vehicles have to obey traffic rules that are set forth in legal documents formulated in natural language. Temporal logic is a suitable concept to formalize such traffic rules. Still, temporal logic rules often result in constraints that are hard to solve using optimization-based motion planners. Reinforcement learning (RL) is a promising method to find motion plans for autonomous vehicles. However, vanilla RL algorithms are based on random exploration and do not automatically comply with traffic rules. Our approach accomplishes guaranteed rule-compliance by integrating temporal logic specifications into RL. Specifically, we consider the application of vessels on the open sea, which must adhere to the Convention on the International Regulations for Preventing Collisions at Sea (COLREGS). To efficiently synthesize rule-compliant actions, we combine predicates based on set-based prediction with a statechart representing our formalized rules and their priorities. Action masking then restricts the RL agent to this set of verified rule-compliant actions. In numerical evaluations on critical maritime traffic situations, our agent always complies with the formalized legal rules and never collides while achieving a high goal-reaching rate during training and deployment. In contrast, vanilla and traffic rule-informed RL agents frequently violate traffic rules and collide even after training.

show abstract

“…In this article, we present an action masking approach, for which the agent can only choose actions that are verified as safe. Most research on action masking considers discrete action spaces; common applications are autonomous driving [36]- [41] and power systems [42]. Usually, the action verification is tailored to the specific application and, thus, cannot be directly transferred to other applications.…”

Section: Related Workmentioning

confidence: 99%

Safe Reinforcement Learning for Urban Driving using Invariably Safe Braking Sets

Krasowski

Zhang

Althoff

2022

2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

Autonomous vehicles have to obey traffic rules. These rules are often formalized using temporal logic, resulting in constraints that are hard to solve using optimization-based motion planners. Reinforcement Learning (RL) is a promising method to find motion plans adhering to temporal logic specifications. However, vanilla RL algorithms are based on random exploration, which is inherently unsafe. To address this issue, we propose a provably safe RL approach that always complies with traffic rules. As a specific application area, we consider vessels on the open sea, which must adhere to the Convention on the International Regulations for Preventing Collisions at Sea (COLREGS). We introduce an efficient verification approach that determines the compliance of actions with respect to the COLREGS formalized using temporal logic. Our action verification is integrated into the RL process so that the agent only selects verified actions. In contrast to agents that only integrate the traffic rule information in the reward function, our provably safe agent always complies with the formalized rules in critical maritime traffic situations and, thus, never causes a collision.

show abstract

Computationally Efficient Safe Reinforcement Learning for Power Systems

Cited by 11 publications

References 27 publications

Pengaruh strategi inovasi dan orientasi pasar terhadap keunggulan bersaing dan kinerja perusahaan (studi pada UKM OKE OCE Jakarta)

Pengaruh strategi inovasi dan orientasi pasar terhadap keunggulan bersaing dan kinerja perusahaan (studi pada UKM OKE OCE Jakarta)

Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea

Safe Reinforcement Learning for Urban Driving using Invariably Safe Braking Sets

Contact Info

Product

Resources

About