Forecasting what Matters: Decision-Focused RL for Controlled EV Charging with Unknown Departure Times

• URL: http://arxiv.org/abs/2606.19199v1
• Date: Wed, 17 Jun 2026 15:37:35 GMT
• Title: Forecasting what Matters: Decision-Focused RL for Controlled EV Charging with Unknown Departure Times
• Abstract summary: In real-world scenarios, key features, such as departure time, often are unavailable.<n>This makes it harder for an RL agent to learn and execute an effective charging policy.<n>We propose a decision-focused RL (DF-RL) framework in which the forecaster is trained end-to-end, i.e., with feedback from the charging policy actions taken by the RL agent.
• Score: 2.6288470934623636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The recent growth of EV adoption poses challenges for power systems, including increased peak demand and potential grid instability. Smart control of EV charging -- e.g., based on reinforcement learning (RL) -- can alleviate these issues by learning temporal and contextual patterns from historical data. Yet, in real-world scenarios, key features, such as departure time, often are unavailable. This, in turn, makes it harder for an RL agent to learn and execute an effective charging policy. To mitigate this uncertainty, a trained forecaster can approximate the unknown features from available data. However, since these forecasting models are typically trained for accuracy (rather than their impact on a downstream agent's decision quality), their errors may propagate and hinder the overall performance of a controller that is using the forecasts. To avoid this, we propose a decision-focused RL (DF-RL) framework in which the forecaster is trained end-to-end, i.e., with feedback from the charging policy actions taken by the RL agent. Such joint training of both the forecaster and controller ultimately results in higher-quality actions: our proposed DF-RL method yields superior charging decisions compared to other baselines, achieving up to a 14% improvement in total reward and a 55% reduction of unsupplied energy (i.e., charging that failed to happen because the EV already left), relative to the RL method without departure time forecasting.

Related papers

• On-Device Adaptive Battery Power Prediction for Electric Vehicles [0.5314069314483559]
  We introduce a novel approach that enables on-device learning in resource-constrained EV systems to continuously adapt pretrained battery prediction models to new, unseen data.<n>Our results demonstrate significant improvements in forecasting performance across various models and time horizons.
  arXiv  Detail & Related papers  (2026-07-10T13:24:34Z)
• RL Forgets! Towards Continual Policy Optimization [57.4336338996653]
  Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.<n>Recent work has increasingly favored reinforcement learning over supervised fine-tuning, driven by the belief that reinforcement learning is inherently less prone to forgetting.<n>We propose Continual Policy Optimization (CPO), a replay-free framework grounded in a prior-task behavioral KL objective.
  arXiv  Detail & Related papers  (2026-07-05T15:46:11Z)
• Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates [53.3717573880076]
  We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates.<n>JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly.<n>Experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods.
  arXiv  Detail & Related papers  (2026-01-26T14:16:51Z)
• Reinforcement Learning on Pre-Training Data [55.570379963147424]
  We introduce Reinforcement Learning on Pre-Training data (R), a new training-time scaling paradigm for optimizing large language models (LLMs)<n>R enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL)<n>Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of R.
  arXiv  Detail & Related papers  (2025-09-23T17:10:40Z)
• Unsupervised Data Generation for Offline Reinforcement Learning: A Perspective from Model [57.20064815347607]
  offline reinforcement learning (RL) recently gains growing interests from RL researchers.<n>The performance of offline RL suffers from the out-of-distribution problem, which can be corrected by feedback in online RL.<n>In this paper, we first build a bridge over the batch data and the performance of offline RL algorithms theoretically.<n>We show that in task-agnostic settings, a series of policies trained by unsupervised RL can minimize the worst-case regret in the performance gap.
  arXiv  Detail & Related papers  (2025-06-24T14:08:36Z)
• Enhancing Battery Storage Energy Arbitrage with Deep Reinforcement Learning and Time-Series Forecasting [3.0382033111760576]
  We conduct a case study using price data from Alberta, Canada that is characterized by irregular price spikes and highly non-stationary. This data is challenging to forecast even when state-of-the-art deep learning models are deployed. Our results show that energy arbitrage with DRL-enabled battery control still significantly benefits from these imperfect predictions.
  arXiv  Detail & Related papers  (2024-10-25T23:18:43Z)
• A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning [54.48409201256968]
  offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of offline pretrained policy using only a few online samples. Most O2O methods focus on the balance between RL objective and pessimism, or the utilization of offline and online samples.
  arXiv  Detail & Related papers  (2023-12-12T19:24:35Z)
• Hybrid Reinforcement Learning for Optimizing Pump Sustainability in Real-World Water Distribution Networks [55.591662978280894]
  This article addresses the pump-scheduling optimization problem to enhance real-time control of real-world water distribution networks (WDNs) Our primary objectives are to adhere to physical operational constraints while reducing energy consumption and operational costs. Traditional optimization techniques, such as evolution-based and genetic algorithms, often fall short due to their lack of convergence guarantees.
  arXiv  Detail & Related papers  (2023-10-13T21:26:16Z)
• Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Driving [4.932817328815897]
  Deep reinforcement learning (DRL) has emerged as a promising approach for developing more intelligent autonomous vehicles (AVs) This work proposes a method to identify and protect unreliable decisions of a DRL driving policy.
  arXiv  Detail & Related papers  (2023-05-12T13:58:31Z)
• Computationally efficient joint coordination of multiple electric vehicle charging points using reinforcement learning [6.37470346908743]
  A major challenge in todays power grid is to manage the increasing load from electric vehicle (EV) charging. We propose a single-step solution that jointly coordinates multiple charging points at once. We show that our new RL solutions still improve the performance of charging demand coordination by 40-50% compared to a business-as-usual policy.
  arXiv  Detail & Related papers  (2022-03-26T13:42:57Z)
• Optimized cost function for demand response coordination of multiple EV charging stations using reinforcement learning [6.37470346908743]
  We build on previous research on RL, based on a Markov decision process (MDP) to simultaneously coordinate multiple charging stations. We propose an improved cost function that essentially forces the learned control policy to always fulfill any charging demand that does not offer flexibility. We rigorously compare the newly proposed batch RL fitted Q-iteration implementation with the original (costly) one, using real-world data.
  arXiv  Detail & Related papers  (2022-03-03T11:22:27Z)
• Learning to Operate an Electric Vehicle Charging Station Considering Vehicle-grid Integration [4.855689194518905]
  We propose a novel centralized allocation and decentralized execution (CADE) reinforcement learning (RL) framework to maximize the charging station's profit. In the centralized allocation process, EVs are allocated to either the waiting or charging spots. In the decentralized execution process, each charger makes its own charging/discharging decision while learning the action-value functions from a shared replay memory. Numerical results show that the proposed CADE framework is both computationally efficient and scalable, and significantly outperforms the baseline model predictive control (MPC)
  arXiv  Detail & Related papers  (2021-11-01T23:10:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.