neural reinforcement 中文意思是什麼
neural reinforcement
解釋
神經強化- neural : adj. 【解剖學】神經（系統）的；神經中樞的；【解剖學】背的，背側的。adv. -ly
- reinforcement : n. 1. 增強，加固；補強物，強化物；補給品。2. 增援，支援；〈pl. 〉增援部隊，援軍；救援艦。
-
In the respect of neural networks control for non - linear and uncertain system, a review of some available control strategy is made. combining neural networks control and conventional control strategy supervised learning, no supervised learning and reinforcement learning neural networks self - studying and adaptive control systems for ship course control are proposed. the thesis studies particularly their characteristics
在非線性和不確定性系統的神經網路控制方面，論文總結了一些現有的神經網路自學習控制系統，然後將神經網路和常規控制（例如pid控制、自適應控制、內模控制等）結合起來，根據船舶操縱的特點，詳細研究和分析了有監督學習、無監督學習和再勵學習的船舶航向神經網路自學習型自適應控制系統。 -
Reinforcement learning algorithms that use cerebellar model articulation controller ( cmac ) are studied to estimate the optimal value function of markov decision processes ( mdps ) with continuous states and discrete actions. the state discretization for mdps using sarsa - learning algorithms based on cmac networks and direct gradient rules is analyzed. two new coding methods for cmac neural networks are proposed so that the learning efficiency of cmac - based direct gradient learning algorithms can be improved
在求解離散行為空間markov決策過程（ mdp ）最優策略的增強學習演算法研究方面，研究了小腦模型關節控制器（ cmac ）在mdp行為值函數逼近中的應用，分析了基於cmac的直接梯度演算法對mdp狀態空間離散化的特點，研究了兩種改進的cmac編碼結構，即：非鄰接重疊編碼和變尺度編碼，以提高直接梯度學習演算法的收斂速度和泛化性能。 -
By means of the proposed reinforcement learning algorithm and modified genetic algorithm, neural network controller whose weights are optimized could generate time series small perturbation signals to convert chaotic oscillations of chaotic systems into desired regular ones. the computer simulations on controlling henon map and logistic chaotic system have demonstrated the capacity of the presented strategy by suppressing lower periodic orbits such as period - 1 and period - 2. meanwhile, the periodic control methodology is utilized, the higher periods such as period - 4 can also be successfully directed to expected periodic orbits
該控制方法無需了解系統的動態特性和精確的數學模型，也不需監督學習所要求的訓練數據，通過增強學習訓練方式，採用改進遺傳演算法優化神經網路權系數，使之成為混沌控制器，便可產生控制混沌系統的時間序列小擾動信號，模擬實驗結果表明它不僅能有效鎮定混沌周期1 、 2等低周期軌道，而且在周期控制技術基礎上，也可成功將高周期混沌軌道（如周期4軌道）變成期望周期行為。
分享友人