Exploration into Optimal State Estimation with Event-triggered Communication
This paper deals with the problem of remote estimation of the state of a discrete-time stochastic linear system observed by a sensor with computational capacity to calculate local estimates. We design an event-triggered communication (ETC) scheme and a remote state estimator to optimally calibrate the tradeoff between system performance and limited communication resources. The novel communication scheme is the time-varying thresholding version for the cumulative innovation-driven communication scheme in [1], and its transmission probability is given. We derive the corresponding remote minimum mean square error (MMSE) estimator and present a tight upper bound for its MSE matrices. We also show that by employing a couple of weak assumptions, the optimality problem becomes (asymptotically) exact and can be addressed in an Markov Decision Process (MDP) framework, which delivers optimal policy and cost in an algorithmic procedure. The simulation results illustrate the effectiveness of our approach.
Code (0)
등록된 구현이 없습니다.
Tasks
State EstimationSimilar Papers 제목 키워드 기반
Optimistic ε-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning
The Centralized Training with Decentralized Execution (CTDE) paradigm is widely used in cooperative multi-agent reinforcement learning. However, due to the representational limitations of traditional monotonic value deco…
Multi-agent Reinforcement LearningExploration and Estimation for Model Compression
Deep neural networks achieve great success in many visual recognition tasks. However, the model deployment is usually subject to some computational resources. Model pruning under computational budget has attracted gr…
modelModel CompressionAn Exploration-Exploitation Approach to Anti-lock Brake Systems
Anti-lock Brake System (ABS) is a mandatory active safety feature on road vehicles with analogous systems for aircraft and locomotives. This feature aims to prevent locking of the wheels when braking and to improve the h…
FrictionConstrained Exploration in Reinforcement Learning with Optimality Preservation
We consider a class of reinforcement-learning systems in which the agent follows a behavior policy to explore a discrete state-action space to find an optimal policy while adhering to some restriction on its behavior. Su…
reinforcement-learningReinforcement LearningProbabilistic Insights for Efficient Exploration Strategies in Reinforcement Learning
We investigate efficient exploration strategies of environments with unknown stochastic dynamics and sparse rewards. Specifically, we analyze first the impact of parallel simulations on the probability of reaching rare s…
DiversityEfficient Explorationreinforcement-learningReinforcement Learning