Effects of sampling and horizon in predictive reinforcement learning

Abstract

Plain reinforcement learning (RL) may be prone to loss of convergence, constraint violation, unexpected performance, etc. Commonly, RL agents undergo extensive learning stages to achieve acceptable functionality. This is in contrast to classical control algorithms which are typically model-based. An direction of research is the fusion of RL with such algorithms, especially model-predictive control (MPC). This, however, introduces new hyper-parameters related to the prediction horizon. Furthermore, RL is usually concerned with Markov decision processes. But the most of the real environments are not time-discrete. The factual physical setting of RL consists of a digital agent and a time-continuous dynamical system. There is thus, in fact, yet another hyper-parameter -- the agent sampling time. In this paper, we investigate the effects of prediction horizon and sampling of two hybrid RL-MPC-agents in a case study with a mobile robot parking, which is in turn a canonical control problem. We benchmark the agents with a simple variant of MPC. The sampling showed a kind of a "sweet spot" behavior, whereas the RL agents demonstrated merits at shorter horizons.

References in corpus (7)

• Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis
• Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning
• Information Theoretic Regret Bounds for Online Nonlinear Control
• Deep Value Model Predictive Control
• Stacked adaptive dynamic programming with unknown system model
• Adaptive Discretization for Model-Based Reinforcement Learning
• Structured Policy Iteration for Linear Quadratic Regulator