Author name cluster

Avishai Halev

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

EAAI Journal 2024 Journal Article

Microgrid control under uncertainty

Avishai Halev
Yongshuai Liu
Xin Liu

Microgrids – decentralized electrical grids that can function both in conjunction with wide area macrogrids and without – are a powerful tool to address energy resiliency and climate change mitigation. Microgrid control, however, remains a challenge; their bespoke nature and the existence of multiple sources of uncertainty lead to a control problem that traditional grid modeling and control techniques are ill-suited to handle. We build a microgrid interface to simulate microgrids under uncertainty and devise off-policy reinforcement learning algorithms to control microgrids. Our algorithms, which incorporate domain randomization and random network distillation for exploration and computational efficiency, achieve performance better than model predictive control and rule based control benchmarks under battery model uncertainty on seven of ten tested scenarios. Our model code is available at https: //github. com/ahalev/Microgrid-Control-Under-Uncertainty and our microgrid simulator is available at https: //github. com/ahalev/python-microgrid.

Details DOI

IJCAI Conference 2021 Conference Paper

Policy Learning with Constraints in Model-free Reinforcement Learning: A Survey

Yongshuai Liu
Avishai Halev
Xin Liu

Reinforcement Learning (RL) algorithms have had tremendous success in simulated domains. These algorithms, however, often cannot be directly applied to physical systems, especially in cases where there are constraints to satisfy (e. g. to ensure safety or limit resource consumption). In standard RL, the agent is incentivized to explore any policy with the sole goal of maximizing reward; in the real world, however, ensuring satisfaction of certain constraints in the process is also necessary and essential. In this article, we overview existing approaches addressing constraints in model-free reinforcement learning. We model the problem of learning with constraints as a Constrained Markov Decision Process and consider two main types of constraints: cumulative and instantaneous. We summarize existing approaches and discuss their pros and cons. To evaluate policy performance under constraints, we introduce a set of standard benchmarks and metrics. We also summarize limitations of current methods and present open questions for future research.

PDF Details DOI