note

matlab reinforcement learning toolboxメモ

観測と行動を配列で渡す複数次元の場合はベクトルを定義して範囲を渡す。 • Simulinkモデル内のエージェントブロックのパス。 強化学習エージェントが接続されるSimulink内のブロックを指定。 obsInfo • 観測値（Observations）の仕様を定義するオブジェクト。
IEEE

Design of adaptive controllers by means of PPO algorithm using MATLAB

Abstract: This paper investigates reinforcement learning (RL) as a practical framework for achieving optimal adaptive control across several simple dynamical system models. All experiments were ...
IEEE

Proof-of-Concept of a Reinforcement-Learning Based RT Shimming Technique for HTS Magnets

Abstract: We report a newly developed room-temperature (RT) shimming method for high-temperature superconducting (HTS) magnets employing a deep Q-network (DQN), a type of reinforcement learning theory ...