Conservative RL

RL: Reinforcement Learning

Latest papers

10 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Offline Reinforcement Learning for Distribution-Grid Protection
Sep 21, 2026Julian Oelhaf, Alexander Luce, Christian Bergler +2Conservative RL Fault Detection
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen–Nürnberg, Erlangen, Germany · Department of Electrical Engineering, Media and Computer Science, Ostbayerische Technische Hochschule Amberg-Weiden, Amberg, Germany
Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations
Sep 17, 2026Zewei Yang, Zengqi Peng, Jun MaAutonomous Parking Conservative RL
Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China · Cheng Kar-Shun Robotics Institute, The Hong Kong University of Science and Technology, Hong Kong SAR, China
SCQ: Stabilizing Conservative Q-Learning with Sigmoid-Bounded Entropy
Sep 11, 2026Xiefeng Wu, Shu Zhang, Zhaojie Chu +1Offline RL Conservative RL
School of Computer Science, Wuhan University, Wuhan, China · School of Electronic Information, Wuhan University, Wuhan, China · School of Internet, Anhui University, Hefei, China
Routing Dense Layouts with History-Aware Offline Reinforcement Learning using LSTM
Sep 8, 2026Afsara Khan, Austin RovinskiReinforcement Learning Conservative RL
New York University Brooklyn, New York, USA
Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models
Jun 29, 2026Subramanyam Sahoo, Aman Chadha, Vinija Jain +1Offline-To-Online RL Reward Hacking
1Horizon Research · 2Apple · 3Meta +1
UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning
May 28, 2026Aditya UpadhyayConservative RL Offline RL
IIIT Delhi
Peng's Q( $λ$ ) for Conservative Value Estimation in Offline Reinforcement Learning
May 14, 2026Byeongchan Kim, Min-hwan OhReinforcement Learning Value Function Estimation
Seoul National University
Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control
Mar 4, 2026Nicolas Helson, Pegah Alizadeh, Anastasios GiovanidisConservative RL Offline RL
Ericsson Research, Massy, France
Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning
Feb 27, 2026Austin A. Nguyen, Michael P. WellmanReinforcement Learning Game Theory
University of Michigan
Flow Actor-Critic for Offline Reinforcement Learning
Feb 20, 2026Jongseong Chae, Jongeui Park, Yongjae Shin +3Flow-Based Policy Learning Conservative RL
KAIST · UNIST

Sep 21, 2026J/K move · Enter open · S save

Offline Reinforcement Learning for Distribution-Grid Protection

Julian Oelhaf, Alexander Luce, Christian Bergler, Andreas Maier+1

Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen–Nürnberg, Erlangen, Germany · Department of Electrical Engineering, Media and Computer Science, Ostbayerische Technische Hochschule Amberg-Weiden, Amberg, Germany

Conservative RL Fault Detection Offline RL Power Systems

Open paper AskPDF arXiv

Data-driven protection may complement conventional relays in distribution grids whose operating conditions vary with distributed generation, switching events, and changing short-circuit levels. We study line-selective tripping from static trajectories of a realistically simulated CIGRE medium-voltage network using offline reinforcement learning. A convolutional Q-network receives causal voltage-current phasor and apparent-impedance features, optionally together with raw waveforms, and is trained with conservative Q-learning (CQL). A controlled sensitivity study evaluates two observation windows, reward variants, and three CQL weights under a common split and training protocol; one exploratory post-hoc run additionally increases the discount factor from

γ

=0.95 to 0.99. On 225 held-out episodes, the best per-timestep result is obtained with combined input and CQL weight

α

=0.9, reaching precision 0.9993, recall 0.9496, and F1-score 0.9738. Because dense per-timestep scores do not encode the terminal semantics of relay operation, we also evaluate the first non-wait action in each episode. The default combined-input agent selects the correct line-trip action first in 98.13% of 214 fault episodes, but trips in 72.73% of the 11 non-fault episodes. In the post-hoc run, the corresponding rates are 98.60% and 54.55%, respectively. The results show that dense predictive performance and terminal protection behavior can lead to different model rankings. Offline CQL therefore demonstrates strong faulted-line selection on the simulated fault episodes, while the static trajectories, small non-fault set, and single-seed post-hoc design preclude conclusions about practical relay security or deployment readiness.