A Micro-Objective Perspective of Reinforcement Learning

2019-05-24 · Changjian Li, Krzysztof Czarnecki

The standard reinforcement learning (RL) formulation considers the expectation of the (discounted) cumulative reward. This is limiting in applications where we are concerned with not only the expected performance, but also the distribution of the performance. In this paper, we introduce micro-objective reinforcement learning --- an alternative RL formalism that overcomes this issue. In this new formulation, a RL task is specified by a set of micro-objectives, which are constructs that specify the desirability or undesirability of events. In addition, micro-objectives allow prior knowledge in the form of temporal abstraction to be incorporated into the global RL objective. The generality of this formalism, and its relations to single/multi-objective RL, and hierarchical RL are discussed.

📄 PDF Abstract BibTeX arXiv:1905.10016

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Multi-Objective Reinforcement Learning based Multi-Microgrid System Optimisation Problem

2021-03-10 · Jiangjiao Xu, Ke Li, Mohammad Abusara

Microgrids with energy storage systems and distributed renewable energy sources play a crucial role in reducing the consumption from traditional power sources and the emission of $CO_2$. Connecting multi microgrid to a d…

energy management Management Multi-Objective Reinforcement Learning reinforcement-learning+2

Micro-Swarm Locomotion Optimization in Dynamic Flow using Multi-Objective Multi-Agent Reinforcement Learning

2026-05-24 · Josef Berman, Oren Gal arxiv

Coordinating micro-robotic swarms in realistic, time-dependent fluid environments remains a major challenge for biomedical and environmental applications. We present a hybrid CFD-MO-MARL (Computational Fluid Dynamics-Mul…

Multi-agent Reinforcement Learning

A General Perspective on Objectives of Reinforcement Learning

2023-06-05 · Long Yang

In this lecture, we present a general perspective on reinforcement learning (RL) objectives, where we show three versions of objectives. The first version is the standard definition of objective in RL literature. Then we…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A Multiobjective Reinforcement Learning Framework for Microgrid Energy Management

2023-07-17 · M. Vivienne Liu, Patrick M. Reed, David Gold, Garret Quist 외

The emergence of microgrids (MGs) has provided a promising solution for decarbonizing and decentralizing the power grid, mitigating the challenges posed by climate change. However, MG operations often involve considering…

energy management Management Multi-Objective Reinforcement Learning reinforcement-learning+1

Fusion of Model-free Reinforcement Learning with Microgrid Control: Review and Vision

2022-06-22 · Buxin She, Fangxing Li, Hantao Cui, Jingqiu Zhang 외

Challenges and opportunities coexist in microgrids as a result of emerging large-scale distributed energy resources (DERs) and advanced control techniques. In this paper, a comprehensive review of microgrid control is pr…

reinforcement-learning Reinforcement Learning (RL)