Lyapunov methods; approximation theory; continuous time systems; convergence of numerical methods; learning (artificial intelligence); nonlinear control systems; stability; state-space methods; Bellman error; Lyapunov-based stability analysis; approximate online adaptive solution; concurrent learning-based system identifier; control-affine continuous-time nonlinear systems; excitation condition; infinite-horizon approximate optimal tracking; model-based reinforcement learning; optimal policy; state space; trajectory tracking; unknown drift dynamics; Artificial neural networks; Function approximation; Optimal control; Stability analysis; Steady-state; Trajectory;
机译:基于模型的无限水平近似最优跟踪强化学习
机译:基于模型的强化学习,用于近似最优调节
机译:基于模型的高效强化学习,用于近似在线最优控制
机译:基于合作模型的加强学习,用于近似最佳跟踪
机译:不确定系统的最优跟踪控制:基于策略和基于策略的强化学习方法
机译:多主体强化学习和近似模型学习的竞技游戏
机译:基于模型的无限近似近似强化学习 最佳跟踪