Data-Aided Channel Estimator for MIMO Systems via Reinforcement Learning

Jeon, Yo-Seb; Li, Jun; Tavangaran, Nima; Poor, H. Vincent

doi:10.1109/icc40277.2020.9149283

Cited by 10 publications

(41 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, a reinforcement learning (RL) approach was introduced in [26] for dataaided channel estimation. In this approach, a Markov decision process (MDP) problem is described to minimize the estimation error, and an RL algorithm is used to solve the MDP problem.…”

Section: Introductionmentioning

confidence: 99%

“…However, this solution is difficult to implement in practical systems because of its considerable complexity and latency in computing the optimal policy. For example, using the approach in [26] to calculate the optimal policy requires all a posteriori probabilities (APPs) in a data block. In addition, its limitation is that the optimal policy is characterized by a specific discounting factor.…”

Section: Introductionmentioning

confidence: 99%

“…An MDP problem is defined for this selection to minimize the mean-square-error (MSE) of the channel estimates. Compared with [26], a discounting factor is introduced in the Q-value function. The discounting factor adjusts the effects of rewards after the current state.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Low-Complexity Algorithm for a Reinforcement Learning-Based Channel Estimator for MIMO Systems

Kim

Min

2022

Sensors

View full text Add to dashboard Cite

This paper proposes a low-complexity algorithm for a reinforcement learning-based channel estimator for multiple-input multiple-output systems. The proposed channel estimator utilizes detected symbols to reduce the channel estimation error. However, the detected data symbols may include errors at the receiver owing to the characteristics of the wireless channels. Thus, the detected data symbols are selectively used as additional pilot symbols. To this end, a Markov decision process (MDP) problem is defined to optimize the selection of the detected data symbols. Subsequently, a reinforcement learning algorithm is developed to solve the MDP problem with computational efficiency. The developed algorithm derives the optimal policy in a closed form by introducing backup samples and data subblocks, to reduce latency and complexity. Simulations are conducted, and the results show that the proposed channel estimator significantly reduces the minimum-mean square error of the channel estimates, thus improving the block error rate compared to the conventional channel estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Low-Complexity Algorithm for a Reinforcement Learning-Based Channel Estimator for MIMO Systems

Kim

Min

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…An RL algorithm for optimizing the symbol vector selection of data-aided channel estimation was first introduced in our prior work [1]. In this algorithm, the optimal policy of the MDP is derived under a simplistic assumption that underestimates the effect of future actions and rewards.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we generalize the RL algorithm in [1] by employing the MCTS approach which provides a more accurate evaluation of the effect of the future actions and rewards. In addition to this major change, we newly introduce the semi-data-aided channel estimation strategy to further reduce the delay required for updating the channel estimate and also introduce the data re-detection strategy to improve detection performance after the symbol vector selection.…”

Section: Introductionmentioning

confidence: 99%

Semi-Data-Aided Channel Estimation for MIMO Systems via Reinforcement Learning

Kim¹,

Jeon²,

Li³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Data-aided channel estimation is a promising solution to improve channel estimation accuracy by exploiting data symbols as pilot signals for updating an initial channel estimate. In this paper, we propose a semi-data-aided channel estimator for multiple-input multiple-output communication systems.Our strategy is to leverage reinforcement learning (RL) for selecting reliable detected symbols among the symbols in the first part of transmitted data block. This strategy facilitates an update of the channel estimate before the end of data block transmission and therefore achieves a significant reduction in communication latency compared to conventional data-aided channel estimation approaches. Towards this end, we first define a Markov decision process (MDP) which sequentially decides whether to use each detected symbol as an additional pilot signal. We then develop an RL algorithm to efficiently find the best policy of the MDP based on a Monte Carlo tree search approach. In this algorithm, we exploit the a-posteriori probability for approximating both the optimal future actions and the corresponding state transitions of the MDP and derive a closed-form expression for the best policy. Simulation results demonstrate that the proposed channel estimator effectively mitigates both channel estimation error and detection performance loss caused by insufficient pilot signals.

show abstract

DRL at the Physical Layer

2023

Deep Reinforcement Learning for Wireless Communications and Networking

View full text Add to dashboard Cite

Data-Aided Channel Estimator for MIMO Systems via Reinforcement Learning

Cited by 10 publications

References 9 publications

A Low-Complexity Algorithm for a Reinforcement Learning-Based Channel Estimator for MIMO Systems

A Low-Complexity Algorithm for a Reinforcement Learning-Based Channel Estimator for MIMO Systems

Semi-Data-Aided Channel Estimation for MIMO Systems via Reinforcement Learning

DRL at the Physical Layer

Contact Info

Product

Resources

About