arXiv subjects

Damien Ernst

Publications and source records attributed to Damien Ernst.

At least 19 recordsLinked to original sources

arXiv2026

Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance

Much like humans benefit from guidance while learning, reinforcement learning algorithms may benefit from additional supervision beyond rewards. Leveraging additional information during training to learn better representations and behaviors has been the focus of asymmetric reinforcement learning. This learning paradigm has proven effective under partial observability when additional state information is available, but also under full observability when more refined state information is available. Focusing on model-based reinforcement learning, we study the effect of asymmetric learning on observation representations and on privileged information representations. First, we identify a limitation in the privileged information representations learned by an asymmetric model-based algorithm known as the Informed Dreamer. Then, we propose a novel asymmetric representation learning objective using latent guidance, resulting in a new algorithm called the Reinformed Dreamer. Experiments across several benchmarks show a more consistent improvement over Dreamer than previous asymmetric approaches.

cs.LG↗

arXiv2026

Fair Allocation of Operating Envelopes for Distribution Networks Considering Voltage Unbalance

Operating envelopes (OEs) are increasingly used to allocate limits to distributed energy resources (DERs) while maintaining secure distribution network operation. In unbalanced low-voltage feeders, OE calculation based only on voltage magnitude and thermal constraints can yield overly optimistic limits because power quality constraints such as voltage unbalance are neglected. This paper proposes a three-phase unbalanced AC optimal power flow framework for computing coupled P--Q OEs with explicit voltage unbalance factor (VUF) constraints. In addition, two fairness mechanisms for allocating the available P--Q flexibility across multiple PV units are embedded and compared: (i) network-weighted proportional fairness and (ii) lexicographic max--min fairness. Case studies on unbalanced test feeders illustrate how VUF constraints reshape the P--Q feasible region and the impact of power quality-constrained operation. The comparison highlights the trade-off between the efficiency, equity, and practicality of fairness allocation methods.

eess.SY↗

arXiv2026

Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications

Sequence learning is dominated by Transformers and parallelizable recurrent neural networks (RNNs) such as state-space models, yet learning long-term dependencies remains challenging, and state-of-the-art designs trade power consumption for performance. The Bistable Memory Recurrent Unit (BMRU) was introduced to enable hardware-software co-design of ultra-low power RNNs: quantized states with hysteresis provide persistent memory while mapping directly to analog primitives. However, BMRU performance lags behind parallelizable RNNs on complex sequential tasks. In this paper, we identify gradient blocking during state updates as a key limitation and propose a cumulative update formulation that restores gradient flow while preserving persistent memory, creating skip-connections through time. This leads to the Cumulative Memory Recurrent Unit (CMRU) and its relaxed variant, the $\alpha$CMRU. Experiments show that the cumulative formulation dramatically improves convergence stability and reduces initialization sensitivity. The CMRU and $\alpha$CMRU match or outperform Linear Recurrent Units (LRUs) and minimal Gated Recurrent Units (minGRUs) across diverse benchmarks at small model sizes, with particular advantages on tasks requiring discrete long-range retention, while the CMRU retains quantized states, persistent memory, and noise-resilient dynamics essential for analog implementation.

cs.LG↗

arXiv2026

Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations

Always-on AI applications, from environmental sensors to biomedical implants, require ultra-low power consumption. Analog circuits offer a path to sub-microwatt inference, yet existing analog implementations are limited to feedforward architectures: extending them to recurrent dynamics has been considered impractical due to noise accumulation through temporal feedback. We demonstrate that this barrier can be overcome through hardware-software co-design. Specifically, we identify that Bistable Memory Recurrent Units (BMRUs), a class of Recurrent Neural Networks (RNNs) with discrete-valued outputs and hysteretic dynamics, admit an ultra-low power current-mode analog implementation which we design from first principles. The resulting circuit establishes a one-to-one correspondence between each learned parameter and a circuit element. The discrete outputs suppress analog noise by at least 20-fold at each cell boundary, breaking the noise accumulation that prevents analog recurrence. We reformulate BMRUs for first-quadrant operation with fixed thresholds, enabling the direct correspondence while preserving expressivity and trainability. Transistor-level simulations in 180 nm Complementary Metal-Oxide-Semiconductor (CMOS) show near-perfect agreement between software predictions and circuit-level behavior, with the software model thereby serving as a high-fidelity simulator of the physical hardware at low computational cost. We leverage this fidelity to conduct large-scale noise immunity and power scaling analyses: the power cost of adding recurrence scales linearly with state dimension, while the feedforward layers dominating total power scale quadratically, meaning recurrence is added at linear marginal cost relative to the feedforward backbone. End-to-end keyword spotting achieves sub-microwatt inference at the RNN core.

cs.AR↗

arXiv2026

Bayesian Inference for Estimating Generation Costs in Electricity Markets

Estimating generation costs from observed electricity market data is essential for market simulation, strategic bidding, and system planning. To that end, we model the relationship between generation costs and production schedules with a latent variable model. Estimating generation costs from observed schedules is then formulated as Bayesian inference. A prior distribution encodes an initial belief on parameters, and the inference consists of updating the belief with the posterior distribution given observations. We use balanced neural posterior estimation (BNPE) to learn this posterior. Validation on the IEEE RTS-96 test system shows that marginal costs are recovered with narrow credible intervals, while start-up costs remain largely unidentifiable from schedules alone. The method is benchmarked against an inverse-optimization algorithm that exhibits larger parameter errors without uncertainty quantification.

eess.SY↗

arXiv2026

Maximum-Entropy Exploration with Future State-Action Visitation Measures

Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by providing additional intrinsic rewards proportional to that entropy function. In this paper, we study intrinsic rewards proportional to the entropy of the discounted distribution of state-action features visited during future time steps. This approach is motivated by two results. First, we show that the expected sum of these intrinsic rewards is a lower bound on the entropy of the discounted distribution of state-action features visited in trajectories starting from the initial states, which we relate to an alternative maximum entropy objective. Second, we show that the distribution used in the intrinsic reward definition is the fixed point of a contraction operator and can therefore be estimated off-policy. Experiments highlight that the new objective leads to improved visitation of features within individual trajectories, in exchange for slightly reduced visitation of features in expectation over different trajectories, as suggested by the lower bound. It also leads to improved convergence speed for learning exploration-only agents. Control performance remains similar across most methods on the considered benchmarks.

cs.LG↗

arXiv2026

Parallelizable memory recurrent units

With the emergence of massively parallel processing units, parallelization has become a desirable property for new sequence models. The ability to parallelize the processing of sequences with respect to the sequence length during training is one of the main factors behind the uprising of the Transformer architecture. However, Transformers lack efficiency at sequence generation, as they need to reprocess all past timesteps at every generation step. Recently, state-space models (SSMs) emerged as a more efficient alternative. These new kinds of recurrent neural networks (RNNs) keep the efficient update of the RNNs while gaining parallelization by getting rid of nonlinear dynamics (or recurrence). SSMs can reach state-of-the art performance through the efficient training of potentially very large networks, but still suffer from limited representation capabilities. In particular, SSMs cannot exhibit persistent memory, or the capacity of retaining information for an infinite duration, because of their monostability. In this paper, we introduce a new family of RNNs, the memory recurrent units (MRUs), that combine the persistent memory capabilities of nonlinear RNNs with the parallelizable computations of SSMs. These units leverage multistability as a source of persistent memory, while getting rid of transient dynamics for efficient computations. We then derive a specific implementation as proof-of-concept: the bistable memory recurrent unit (BMRU). This new RNN is compatible with the parallel scan algorithm. We show that BMRU achieves good results in tasks with long-term dependencies, and can be combined with state-space models to create hybrid networks that are parallelizable and have transient dynamics as well as persistent memory.

cs.LG↗

arXiv2025

Gym-TORAX: Open-source software for integrating reinforcement learning with plasma control simulators in tokamak research

This paper presents Gym-TORAX, a Python package enabling the implementation of Reinforcement Learning (RL) environments for simulating plasma dynamics and control in tokamaks. Users define succinctly a set of control actions and observations, and a control objective from which Gym-TORAX creates a Gymnasium environment that wraps TORAX for simulating the plasma dynamics. The objective is formulated through rewards depending on the simulated state of the plasma and control action to optimize specific characteristics of the plasma, such as performance and stability. The resulting environment instance is then compatible with a wide range of RL algorithms and libraries and will facilitate RL research in plasma control. In its current version, one environment is readily available, based on a ramp-up scenario of the International Thermonuclear Experimental Reactor (ITER).

cs.LG↗

arXiv2025

SecuLEx: a Secure Limit Exchange Market for Dynamic Operating Envelopes

Distributed energy resources (DERs) are transforming power networks, challenging traditional operational methods, and requiring new coordination mechanisms. To address this challenge, this paper introduces SecuLEx (Secure Limit Exchange), a new market-based paradigm to allocate power injection and withdrawal limits that guarantee network security during time periods, called dynamic operating envelopes (DOEs). Under this paradigm, distribution system operators (DSOs) assign initial DOEs to customers. These limits can be exchanged afterward through a market, allowing customers to reallocate them according to their needs while ensuring network operational constraints. We formalize SecuLEx and illustrate DOE allocation and market exchanges on a small-scale low-voltage (LV) network, demonstrating that both procedures are computationally tractable. In this example, SecuLEx reduces renewable curtailment and improves grid utilization and social welfare compared to traditional approaches.

eess.SY↗

arXiv2025

Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access

Asymmetric reinforcement learning leverages privileged information available during training to improve learning under partial observability. Existing asymmetric actor-critic methods typically assume access to the full environment state to condition the critic during training, which is often unrealistic in practice. We introduce the informed asymmetric actor-critic framework that allows the critic to be conditioned on arbitrary state-dependent privileged signals, and show that any such signal yields unbiased policy gradient estimates. This substantially expands the set of admissible privileged information and raises the problem of selecting the most informative signals for learning. To this end, we propose two novel informativeness criteria: a dependence-based test that can be applied prior to training, and a test based on improvements in value prediction that can be applied post hoc. Experiments on partially observable benchmarks and synthetic environments demonstrate that carefully selected privileged signals can match or outperform full-state asymmetric baselines while relying on strictly less state information.

cs.LG↗

arXiv2025

Fast reconstruction of degenerate populations of conductance-based neuron models from spike times

Inferring the biophysical parameters of conductance-based models (CBMs) from experimentally accessible recordings remains a central challenge in computational neuroscience. Spike times are the most widely available data, yet they reveal little about which combinations of ion channel conductances generate the observed activity. This inverse problem is further complicated by neuronal degeneracy, where multiple distinct conductance sets yield similar spiking patterns. We introduce a method that addresses this challenge by combining deep learning with Dynamic Input Conductances (DICs), a theoretical framework that reduces complex CBMs to three interpretable feedback components governing excitability and firing patterns. Our approach first maps spike times to DIC densities at threshold using a neural network that learns a low-dimensional representation of neuronal activity. The predicted DIC values are then used to generate degenerate CBM populations via an iterative compensation algorithm, ensuring compatibility with the intermediate target DICs, and thereby reproducing the corresponding firing patterns, even in high-dimensional models. Applied to two models, this algorithmic pipeline reconstructs spiking and bursting regimes with high accuracy and robustness to variability, including spike trains generated under noisy current injection mimicking physiological stochasticity. It produces diverse degenerate populations within milliseconds on standard hardware, enabling scalable and efficient inference from spike recordings alone. Together, this work positions DICs as a practical and interpretable link between experimentally observed activity and mechanistic models. By enabling fast and scalable reconstruction of degenerate populations directly from spike times, our approach provides a powerful way to investigate how neurons exploit conductance variability to achieve reliable computation.

q-bio.NC↗

arXiv2025

Remote Renewable Energy Hubs: a Taxonomy

Serving the energy demand with renewable energy is hindered by its limited availability near load centres (i.e. places where the energy demand is high). To address this challenge, the concept of Remote Renewable Energy Hubs (RREH) emerges as a promising solution. RREHs are energy hubs located in areas with abundant renewable energy sources, such as sun in the Sahara Desert or wind in Greenland. In these hubs, renewable energy sources are used to synthetise energy molecules. To produce specific energy molecules, a tailored hub configuration must be designed, which means choosing a set of technologies that are interacting with each other as well as defining how they are integrated in their local environment. The plurality of technologies that may be employed in RREHs results in a large diversity of hubs. In order to characterize this diversity, we propose in this paper a taxonomy for accurately defining these hubs. This taxonomy allows to better describe and compare designs of hubs as well as to identify new ones. Thus, it may guide policymakers and engineers in hub design, contributing to cost efficiency and/or improving local integration.

eess.SY↗

arXiv2025

Ammonia, Methane, Hydrogen and Methanol Produced in Remote Renewable Energy Hubs: a Comparative Quantitative Analysis

Remote renewable energy hubs (RREHs) for synthetic fuel production are engineering systems harvesting renewable energy where it is particularly abundant. They produce transportable synthetic fuels for export to distant load centers. This article aims to evaluate the production costs of different energy carriers, and includes a discussion on advantages and disadvantages in terms of technical performance. To do so, we extend the study of Berger et al., (2021) which focuses on methane (CH4) as energy carrier and introduce three new carriers: ammonia (NH3), hydrogen (H2) and methanol (CH3OH). The four different RREHs are located in the Algerian Sahara desert and must serve to the load center, Belgium, a constant electro-fuel demand of 10 TWh per year. The modelling and optimisation of these systems are performed using the modelling language GBOML (Graph-Based Optimisation Modelling Language). Our findings reveal that the three new RREHs, each with its respective carrier (ammonia, hydrogen, and methanol), are all more cost-effective than the methane-based system. Ammonia demonstrates the most favourable cost-to-energy exported ratio.

eess.SY↗

arXiv2025

How to craft a deep reinforcement learning policy for wind farm flow control

Within wind farms, wake effects between turbines can significantly reduce overall energy production. Wind farm flow control encompasses methods designed to mitigate these effects through coordinated turbine control. Wake steering, for example, consists in intentionally misaligning certain turbines with the wind to optimize airflow and increase power output. However, designing a robust wake steering controller remains challenging, and existing machine learning approaches are limited to quasi-static wind conditions or small wind farms. This work presents a new deep reinforcement learning methodology to develop a wake steering policy that overcomes these limitations. Our approach introduces a novel architecture that combines graph attention networks and multi-head self-attention blocks, alongside a novel reward function and training strategy. The resulting model computes the yaw angles of each turbine, optimizing energy production in time-varying wind conditions. An empirical study conducted on steady-state, low-fidelity simulation, shows that our model requires approximately 10 times fewer training steps than a fully connected neural network and achieves more robust performance compared to a strong optimization baseline, increasing energy production by up to 14 %. To the best of our knowledge, this is the first deep reinforcement learning-based wake steering controller to generalize effectively across any time-varying wind conditions in a low-fidelity, steady-state numerical simulation setting.

cs.LG↗

arXiv2025

A Theoretical Justification for Asymmetric Actor-Critic Algorithms

In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages additional state information available at training time for faster learning. Although the proposed learning objectives are usually theoretically sound, these methods still lack a precise theoretical justification for their potential benefits. We propose such a justification for asymmetric actor-critic algorithms with linear function approximators by adapting a finite-time convergence analysis to this setting. The resulting finite-time bound reveals that the asymmetric critic eliminates error terms arising from aliasing in the agent state.

cs.LG↗

arXiv2025

Investigating the Monte-Carlo Tree Search Approach for the Job Shop Scheduling Problem

The Job Shop Scheduling Problem (JSSP) is a well-known optimization problem in manufacturing, where the goal is to determine the optimal sequence of jobs across different machines to minimize a given objective. In this work, we focus on minimising the weighted sum of job completion times. We explore the potential of Monte Carlo Tree Search (MCTS), a heuristic-based reinforcement learning technique, to solve large-scale JSSPs, especially those with recirculation. We propose several Markov Decision Process (MDP) formulations to model the JSSP for the MCTS algorithm. In addition, we introduce a new synthetic benchmark derived from real manufacturing data, which captures the complexity of large, non-rectangular instances often encountered in practice. Our experimental results show that MCTS effectively produces good-quality solutions for large-scale JSSP instances, outperforming our constraint programming approach.

cs.AI↗

arXiv2025

Efficient LP warmstarting for linear modifications of the constraint matrix

We consider the problem of computing the optimal solution and objective of a linear program under linearly changing linear constraints. The problem studied is given by $\min c^t x \text{ s.t } Ax + \lambda Dx \leq b$ where $\lambda$ belongs to a set of predefined values $\Lambda$. Based on the information given by a precomputed basis, we present three efficient LP warm-starting algorithms. Each algorithm is either based on the eigenvalue decomposition, the Schur decomposition, or a tweaked eigenvalue decomposition to evaluate the optimal solution and optimal objective of these problems. The three algorithms have an overall complexity $O(pm^2+pmn)$ where $m$ (resp. $n$) is the number of constraints (resp. variables) of the original problem and $p$ the number of values in $\Lambda$ after an initial preprocessing step. We also provide theorems related to the optimality conditions to verify when a basis is still optimal and a local bound on the objective.

math.OC↗

arXiv2024

Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures

Maximum entropy reinforcement learning integrates exploration into policy learning by providing additional intrinsic rewards proportional to the entropy of some distribution. In this paper, we propose a novel approach in which the intrinsic reward function is the relative entropy of the discounted distribution of states and actions (or features derived from these states and actions) visited during future time steps. This approach is motivated by two results. First, a policy maximizing the expected discounted sum of intrinsic rewards also maximizes a lower bound on the state-action value function of the decision process. Second, the distribution used in the intrinsic reward definition is the fixed point of a contraction operator. Existing algorithms can therefore be adapted to learn this fixed point off-policy and to compute the intrinsic rewards. We finally introduce an algorithm maximizing our new objective, and we show that resulting policies have good state-action space coverage and achieve high-performance control.

cs.LG↗