Driving Reinforcement Learning with Models
This addresses the challenge of enhancing reinforcement learning efficiency for tasks like game playing, though it appears incremental as it builds on existing RL and MPC methods.
The paper tackles the problem of improving reinforcement learning performance by combining it with model-based control (specifically Model Predictive Control) in a novel algorithm called MPC augmented RL (MPRL), demonstrating that MPRL outperforms both RL and MPC individually when playing the Atari game Pong.
In this paper we propose a new approach to complement reinforcement learning (RL) with model-based control (in particular, Model Predictive Control - MPC). We introduce an algorithm, the MPC augmented RL (MPRL) that combines RL and MPC in a novel way so that they can augment each other's strengths. We demonstrate the effectiveness of the MPRL by letting it play against the Atari game Pong. For this task, the results highlight how MPRL is able to outperform both RL and MPC when these are used individually.