Shielded Deep Reinforcement Learning for Complex Spacecraft Tasking

2024-03-08 · Robert Reed, Hanspeter Schaub, Morteza Lahijanian

Autonomous spacecraft control via Shielded Deep Reinforcement Learning (SDRL) has become a rapidly growing research area. However, the construction of shields and the definition of tasking remains informal, resulting in policies with no guarantees on safety and ambiguous goals for the RL agent. In this paper, we first explore the use of formal languages, namely Linear Temporal Logic (LTL), to formalize spacecraft tasks and safety requirements. We then define a manner in which to construct a reward function from a co-safe LTL specification automatically for effective training in SDRL framework. We also investigate methods for constructing a shield from a safe LTL specification for spacecraft applications and propose three designs that provide probabilistic guarantees. We show how these shields interact with different policies and the flexibility of the reward structure through several experiments.

📄 PDF Abstract BibTeX arXiv:2403.05693

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning

Multi-Spacecraft Predictive Sensor Tasking for Cislunar Space Situational Awareness

2023-10-07 · Kento Tomita, Yuri Shimane, Koki Ho

This paper delves into the predictive sensor tasking algorithm for the multi-observer, multi-target sensor setting, leveraging the Extended Information Filter (EIF). Conventional predictive formulations suffer from the c…

Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learning

2024-11-07 · Satchit Chatterji, Erman Acar

Safe reinforcement learning (RL) is crucial for real-world applications, and multi-agent interactions introduce additional safety challenges. While Probabilistic Logic Shields (PLS) has been a powerful proposal to enforc…

Multi-agent Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+2

Deep Reinforcement Learning for Scalable Multiagent Spacecraft Inspection

2024-12-13 · Kyle Dunlap, Nathaniel Hamilton, Kerianne L. Hobbs

As the number of spacecraft in orbit continues to increase, it is becoming more challenging for human operators to manage each mission. As a result, autonomous control methods are needed to reduce this burden on operator…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Run Time Assured Reinforcement Learning for Six Degree-of-Freedom Spacecraft Inspection

2024-06-17 · Kyle Dunlap, Kochise Bennett, David van Wijk, Nathaniel Hamilton 외

The trial and error approach of reinforcement learning (RL) results in high performance across many complex tasks, but it can also lead to unsafe behavior. Run time assurance (RTA) approaches can be used to assure safety…

Reinforcement Learning (RL)

Shielded RecRL: Explanation Generation for Recommender Systems without Ranking Degradation

2025-10-14 · Ansh Tiwari, Ayush Chauhan arxiv

We introduce Shielded RecRL, a reinforcement learning approach to generate personalized explanations for recommender systems without sacrificing the system's original ranking performance. Unlike prior RLHF-based recommen…

Reinforcement Learning Explanation Generation