Driving Reinforcement Learning With Models

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrathi2019driving

Related papers

• Model Predictive Control And Reinforcement Learning: A Unified Framework Based On Dynamic Programming (2024)10.61
• Model-based Reinforcement Learning For Atari (2019)0.00
• PC-MLP: Model-based Reinforcement Learning With Policy Cover Guided Exploration (2021)0.00
• Towards An Adaptable And Generalizable Optimization Engine In Decision And Control: A Meta Reinforcement Learning Approach (2024)0.00
• Model Predictive Control With Self-supervised Representation Learning (2023)0.00
• Blending MPC & Value Function Approximation For Efficient Reinforcement Learning (2020)0.00
• Robust Model-based Reinforcement Learning With An Adversarial Auxiliary Model (2024)0.00
• Information Theoretic Model Predictive Q-learning (2019)0.00