Enhancing reinforcement learning by a finite reward response filter with a case study in intelligent structural control

no code implementations • 25 Oct 2020 • Hamid Radmard Rahmani, Carsten Koenke, Marco A. Wiering

In many reinforcement learning (RL) problems, it takes some time until a taken action by the agent reaches its maximum effect on the environment and consequently the agent receives the reward corresponding to that action by a delay called action-effect delay.

Q-Learning reinforcement-learning +1