Self-Adaptive Swarm System (SASS)

The widespread application of artificial intelligence technology in various fields has made the sustainable development of artificial intelligence courses an important direction in the field of artificial intelligence education and teaching. Therefore, it is particularly important to conduct an in-depth analysis of the current research status of “artificial intelligence courses” from a global perspective. Firstly, this article clarifies the three stages of slow development, rapid development, and mature development of artificial intelligence curriculum research through the number and distribution years of the literature. It also conducts a co-authorship analysis on the distribution of countries, institutions, and authors of artificial intelligence curriculum research and identifies countries, institutions, and core authors that have made greater contributions to artificial intelligence curriculum research. Secondly, due to the involvement of artificial intelligence in many different fields of knowledge, an analysis is conducted on the journals that published papers on artificial intelligence courses. Finally, based on the analysis of keyword density and time span, the current research hotspots of artificial intelligence courses are summarized: artificial intelligence technology empowerment courses, two education directions at different stages of artificial intelligence courses, and teaching forms in the field of artificial intelligence courses. The current research trend of artificial intelligence courses is analyzed from three aspects: teaching format, teaching content, and teaching objects. This article provides a theoretical reference value and practical basis for future research and development in the field of artificial intelligence courses, while also providing experience for the efficient and sustainable development of artificial intelligence courses to a certain extent.

show abstract

“…Fig. 6 illustrates the Agent Needs Hierarchy as five different modules in the proposed Self-Adaptive Swarm Systems (SASS) [53].…”

Section: Motivational Systemsmentioning

confidence: 99%

Research Status and Challenges on the Sustainable Development of Artificial Intelligence Courses from a Global Perspective

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Specifically, it defines five different levels of agent needs similar to Maslow's human needs pyramid (Yang andParasuraman 2021, 2023a). The lowest (first) level is the safety features of the agent (e.g., features such as collision detection, fault detection, etc., that assure safety to the agent, human, and other friendly agents in the environment).…”

Section: Agent Needs Hierarchymentioning

confidence: 99%

“…More specifically, the set of agent needs in a multi-agent system can be regarded as a kind of motivation or requirements for cooperation between agents to achieve a specific group-level task (Yang 2022).…”

Section: Agent Needs Hierarchymentioning

confidence: 99%

“…It exhibits the fundamental properties of agents' perception, reasoning, planning, decision-making, learning, problem-solving, and communication in interaction with dynamic and complex environments (Langley, Laird, and Rogers 2009;Yang et al 2019). Especially in the field of real-time strategy (RTS) game (Buro 2003;Yang and Parasuraman 2022) and real-world implementation scenarios like robot-aided urban search and rescue (USAR) missions (Murphy 2014;Yang and Parasuraman 2020b), agents need to dynamically change the strategies adapting to the current situations based on the environments and their expected utilities or needs (Yang andParasuraman 2020a, 2021).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Reinforcement Learning

Huang¹

2020

Deep Reinforcement Learning

View full text Add to dashboard Cite

The needs describe the necessities for a self-organizing system to survive and evolve, which arouses an agent to action toward a goal, giving purpose and direction to behavior. Based on Maslow's hierarchy of needs, an agent needs to satisfy a certain amount of needs at the current level as a condition to arise at the next stage -upgrade and evolution. Especially, Deep Reinforcement Learning (DAL) can help AI agents (like robots) organize and optimize their behaviors and strategies to develop diverse Strategies based on their current state and needs (expected utilities or rewards). This paper introduces the new hierarchical needs-driven Learning systems based on DAL and investigates the implementation in the single-robot with a novel approach termed Bayesian Soft Actor-Critic (BSAC). Then, we extend this topic to the Multi-Agent systems (MAS), discussing the potential research fields and directions.

show abstract

“…More specially, in reinforcement learning (RL), the policy dictates the actions that the agent takes as a function of its state and the environment, and the goal of the agent is to learn a policy maximizing the expected cumulative rewards in the process. With advancements in deep neural network implementations, deep reinforcement learning (DRL) helps AI agents master more complex strategy (policy) and represents a step toward building autonomous systems with a higher-level understanding of the visual world [1,18].…”

Section: Introductionmentioning

confidence: 99%

A Strategy-Oriented Bayesian Soft Actor-Critic Model

Qin¹,

Parasuraman²

2023

Preprint

View full text Add to dashboard Cite

Adopting reasonable strategies is challenging but crucial for an intelligent agent with limited resources working in hazardous, unstructured, and dynamic environments to improve the system's utility, decrease the overall cost, and increase mission success probability. This paper proposes a novel hierarchical strategy decomposition approach based on the Bayesian chain rule to separate an intricate policy into several simple sub-policies and organize their relationships as Bayesian strategy networks (BSN). We integrate this approach into the state-of-the-art DRL method -soft actor-critic (SAC) and build the corresponding Bayesian soft actor-critic (BSAC) model by organizing several sub-policies as a joint policy. We compare the proposed BSAC method with the SAC and other state-of-the-art approaches such as TD3, DDPG, and PPO on the standard continuous control benchmarks -Hopper-v2, Walker2d-v2, and Humanoid-v2 -in MuJoCo with the OpenAI Gym environment. The results demonstrate that the promising potential of the BSAC method significantly improves training efficiency.

show abstract

Self-Adaptive Swarm System (SASS)

Cited by 3 publications

References 0 publications

Research Status and Challenges on the Sustainable Development of Artificial Intelligence Courses from a Global Perspective

Research Status and Challenges on the Sustainable Development of Artificial Intelligence Courses from a Global Perspective

Hierarchical Reinforcement Learning

A Strategy-Oriented Bayesian Soft Actor-Critic Model

Contact Info

Product

Resources

About