Search Results for author:
Found 34 papers, 13 papers with code
Behind the Myth of Exploration in Policy Gradients
To compute near-optimal policies, it is essential in practice to include exploration terms in the learning objective.
Optimal Control of Renewable Energy Communities subject to Network Peak Fees with Model Predictive Control and Reinforcement Learning Algorithms
We propose in this paper an optimal control framework for renewable energy communities (RECs) equipped with controllable assets.
Informed POMDP: Leveraging Additional Information in Model-Based RL
We then show that this informed objective consists of learning an environment model from which we can sample latent trajectories.
IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL
We introduce IMP-MARL, an open-source suite of multi-agent reinforcement learning (MARL) environments for large-scale Infrastructure Management Planning (IMP), offering a platform for benchmarking the scalability of cooperative MARL methods in real-world engineering applications.
Spike-based computation using classical recurrent neural networks
We show that this new network can achieve performance comparable to other types of spiking networks in the MNIST benchmark and its variants, the Fashion-MNIST and the Neuromorphic-MNIST.
Policy Gradient Algorithms Implicitly Optimize by Continuation
First, we formulate direct policy optimization in the optimization by continuation framework.
Matching of Everyday Power Supply and Demand with Dynamic Pricing: Problem Formalisation and Conceptual Analysis
At its core, this idea consists in providing the consumer with a price signal which is evolving over time, in order to influence its consumption.
Risk-Sensitive Policy with Distributional Reinforcement Learning
Classical reinforcement learning (RL) techniques are generally concerned with the design of decision-making policies driven by the maximisation of the expected outcome.
Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition
In this paper, we identify the best learning scenario to train a team of agents to compete against multiple possible strategies of opposing teams.
Recurrent networks, hidden states and beliefs in partially observable environments
In summary, this work shows that in its hidden states, a recurrent neural network approximating the Q-function of a partially observable environment reproduces a sufficient statistic from the history that is correlated to the relevant part of the belief for taking optimal actions.
Churn prediction in online gambling
To evaluate the performances of the trained models, standard machine learning metrics were used, such as accuracy, precision and recall.
Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks
The results highlight the main strengths and weaknesses associated with each probability metric together with an important limitation of the Wasserstein distance.
Distributional Reinforcement Learning
reinforcement-learning
+2
Warming up recurrent neural networks to maximise reachable multistability greatly improves learning
This insight leads to the design of a novel way to initialise any recurrent cell connectivity through a procedure called "warmup" to improve its capability to learn arbitrarily long time dependencies.
M4Depth: Monocular depth estimation for autonomous vehicles in unseen environments
We use these cost volumes to leverage the visual spatio-temporal constraints imposed by motion and to make the network robust for varied scenes.
Ranked #2 on
Monocular Depth Estimation
on Mid-Air Dataset
Gym-ANM: Open-source software to leverage reinforcement learning for power system management in research and education
Gym-ANM is a Python package that facilitates the design of reinforcement learning (RL) environments that model active network management (ANM) tasks in electricity networks.
Model Reduction in Capacity Expansion Planning Problems via Renewable Generation Site Selection
The accurate representation of variable renewable generation (RES, e. g., wind, solar PV) assets in capacity expansion planning (CEP) studies is paramount to capture spatial and temporal correlations that may exist between sites and impact both power system design and operation.
Gym-ANM: Reinforcement Learning Environments for Active Network Management Tasks in Electricity Distribution Systems
In this work, we introduce Gym-ANM, a framework for designing reinforcement learning (RL) environments that model ANM tasks in electricity distribution networks.
Sparse Training Theory for Scalable and Efficient Agents
A fundamental task for artificial intelligence is learning.
Remote Renewable Hubs For Carbon-Neutral Synthetic Fuel Production
The framework is leveraged to study the economics of carbon-neutral synthetic methane production from solar and wind energy in North Africa and its delivery to Northwestern European markets.
QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
This paper introduces four new algorithms that can be used for tackling multi-agent reinforcement learning (MARL) problems occurring in cooperative settings.
Assessing the Impact of Offshore Wind Siting Strategies on the Design of the European Power System
In addition, two variants of these siting schemes are provided, wherein the number of sites to be selected is specified on a country-by-country basis rather than Europe-wide.
Allocation of locally generated electricity in renewable energy communities
Local electricity markets represent a way of supplementing traditional retailing contracts for end consumers -- among these markets, the renewable energy community has gained momentum over the last few years.
An Artificial Intelligence Solution for Electricity Procurement in Forward Markets
In this scientific article, the focus is set on a yearly base load product from the Belgian forward market, named calendar (CAL), which is tradable up to three years ahead of the delivery period.
A bio-inspired bistable recurrent cell allows for long-lasting memory
Standard gated cells share a layer internal state to store information at the network level, and long term memory is shaped by network-wide recurrent connection weights.
Jointly Learning Environments and Control Policies with Projected Stochastic Gradient Ascent
We assess the performance of our algorithm in three environments concerned with the design and control of a mass-spring-damper system, a small-scale off-grid power system and a drone, respectively.
A Deep Reinforcement Learning Framework for Continuous Intraday Market Bidding
In this paper, we propose a novel modelling framework for the strategic participation of energy storage in the European continuous intraday market where exchanges occur through a centralized order book.
An Application of Deep Reinforcement Learning to Algorithmic Trading
This scientific research paper presents an innovative approach based on deep reinforcement learning (DRL) to solve the algorithmic trading problem of determining the optimal trading position at any point in time during a trading activity in stock markets.
Introducing Neuromodulation in Deep Neural Networks to Learn Adaptive Behaviours
Animals excel at adapting their intentions, attention, and actions to the environment, making them remarkably efficient at interacting with a rich, unpredictable and ever-changing external world, a property that intelligent machines currently lack.
On overfitting and asymptotic bias in batch reinforcement learning with partial observability
This paper provides an analysis of the tradeoff between asymptotic bias (suboptimality with unlimited data) and overfitting (additional suboptimality due to limited data) in the context of reinforcement learning with partial observability.
How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies
When the discount factor progressively increases up to its final value, we empirically show that it is possible to significantly reduce the number of learning steps.
Benchmarking for Bayesian Reinforcement Learning
In order to enable the comparison of non-anytime algorithms, our methodology also includes a detailed analysis of the computation time requirement of each algorithm.
Simple connectome inference from partial correlation statistics in calcium imaging
In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data.
Toggling a Genetic Switch Using Reinforcement Learning
In this paper, we consider the problem of optimal exogenous control of gene regulatory networks.
Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality
We consider an original problem that arises from the issue of security analysis of a power system and that we name optimal discovery with probabilistic expert advice.
