SeMiner: Side-Information-Based Semantics Miner for Proprietary Industrial Control Protocols

Cai, Jun; Zhong, Weijian; Luo, Jianzhen

doi:10.1109/jiot.2022.3185649

Cited by 3 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, an agent i obtains a local observation o i (t) -which is equivalent to its own location in the grid world. By following equation ( 1), the state of the environment s(t) at time step t is defined as the location of all agents in the grid world 10 . Each agent i, using its quantization/communication policy, generates a compressed version c i (t) of its observation to be communicated to the CC via a bit-budgeted communication link.…”

Section: A the Geometric Consensus Problemmentioning

confidence: 99%

“…(iii) effectiveness problem: given channel and network constraints, how accurately the communication symbols can help to fulfil the desired task? While the traditional communication design addresses the technical problem, recently, the semantic problem [2], [3], [5], [9], [10] as well as the effectiveness problem [6], [11]- [18] have attracted extensive research interest.…”

Section: Introductionmentioning

confidence: 99%

“…The same conditions are true for the control actions of arbitrary agents 5. As defined in the literature[10], the underlying MDP' is the horizon-T ′ MDP defined by a hypothetical single agent that takes joint actions m(t) ∈ M N and observes the nominal state s(t) ≜ ⟨o 1 (t), . .…”

mentioning

confidence: 99%

“…We only assume the presence of an underlying MDP for the environment, which is widely adopted in the literature for the reinforcement learning algorithm, e.g.,[37] [38]. We have this assumption as our performance guarantees rely on the optimality of the solution provided for the control task, which is also assumed in[7],[10]. Let us recall that throughout all of our numerical studies, even the CC, given joint observations of all agents, cannot observe the true/nominal state of the environment.This article has been accepted for publication in IEEE Internet of Things Journal.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Task-Effective Compression of Observations for the Centralized Control of a Multiagent System Over Bit-Budgeted Channels

Mostaani,

Vu,

Chatzinotas

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

We consider a task-effective quantization problem that arises when multiple agents are controlled via a centralized controller (CC). While agents have to communicate their observations to the CC for decision-making, the bit-budgeted communications of agent-CC links may limit the task-effectiveness of the system which is measured by the system's average sum of stage costs/rewards. As a result, each agent should compress/quantize its observation such that the average sum of stage costs/rewards of the control task is minimally impacted. We address the problem of maximizing the average sum of stage rewards by proposing two different Action-Based State Aggregation (ABSA) algorithms that carry out the indirect and joint design of control and communication policies in the multi-agent system. While the applicability of ABSA-1 is limited to single-agent systems, it provides an analytical framework that acts as a stepping stone to the design of ABSA-2. ABSA-2 carries out the joint design of control and communication for a multi-agent system. We evaluate the algorithms -with average return as the performance metric -using numerical experiments performed to solve a multi-agent geometric consensus problem. The numerical results are concluded by introducing a new metric that measures the effectiveness of communications in a multi-agent system.

show abstract

Section: A the Geometric Consensus Problemmentioning

confidence: 99%