Author name cluster

Ludovic Denoyer

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.

13 papers

2 author rows

ICLR Conference 2025 Conference Paper

Efficient Active Imitation Learning with Random Network Distillation

Emilien Biré
Anthony Kobanda
Ludovic Denoyer
Rémy Portelas

Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games, where simulated players (bots) need to play realistically, and there is no clear reward to evaluate them. While imitation learning has shown promise in such domains, these methods often fail when agents encounter out-of-distribution scenarios during deployment. Expanding the training dataset is a common solution, but it becomes impractical or costly when relying on human demonstrations. This article addresses active imitation learning, aiming to trigger expert intervention only when necessary, reducing the need for constant expert input along training. We introduce Random Network Distillation DAgger (RND-DAgger), a new active imitation learning method that limits expert querying by using a learned state-based out-of-distribution measure to trigger interventions. This approach avoids frequent expert-agent action comparisons, thus making the expert intervene only when it is useful. We evaluate RND-DAgger against traditional imitation learning and other active approaches in 3D video games (racing and third-person navigation) and in a robotic locomotion task and show that RND-DAgger surpasses previous methods by reducing expert queries. https://sites.google.com/view/rnd-dagger

Details

ICLR Conference 2023 Conference Paper

Building a Subspace of Policies for Scalable Continual Learning

Jean-Baptiste Gaya
Thang Doan
Lucas Caccia
Laure Soulier
Ludovic Denoyer
Roberta Raileanu

The ability to continuously acquire new knowledge and skills is crucial for autonomous agents. Existing methods are typically based on either fixed-size models that struggle to learn a large number of diverse behaviors, or growing-size models that scale poorly with the number of tasks. In this work, we aim to strike a better balance between scalability and performance by designing a method whose size grows adaptively depending on the task sequence. We introduce Continual Subspace of Policies (CSP), a new approach that incrementally builds a subspace of policies for training a reinforcement learning agent on a sequence of tasks. The subspace's high expressivity allows CSP to perform well for many different tasks while growing more slowly than the number of tasks. Our method does not suffer from forgetting and also displays positive transfer to new tasks. CSP outperforms a number of popular baselines on a wide range of scenarios from two challenging domains, Brax (locomotion) and Continual World (robotic manipulation). Interactive visualizations of the subspace can be found at https://share.streamlit.io/continual-subspace/policies/main.

Details

ICLR Conference 2022 Conference Paper

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching

Pierre-Alexandre Kamienny
Jean Tarbouriech
Sylvain Lamprier
Alessandro Lazaric
Ludovic Denoyer

Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning. A desirable and challenging unsupervised objective is to learn a set of diverse skills that provide a thorough coverage of the state space while being directed, i.e., reliably reaching distinct regions of the environment. In this paper, we build on the mutual information framework for skill discovery and introduce UPSIDE, which addresses the coverage-directedness trade-off in the following ways: 1) We design policies with a decoupled structure of a directed skill, trained to reach a specific region, followed by a diffusing part that induces a local coverage. 2) We optimize policies by maximizing their number under the constraint that each of them reaches distinct regions of the environment (i.e., they are sufficiently discriminable) and prove that this serves as a lower bound to the original mutual information objective. 3) Finally, we compose the learned directed skills into a growing tree that adaptively covers the environment. We illustrate in several navigation and control environments how the skills learned by UPSIDE solve sparse-reward downstream tasks better than existing baselines.

Details

ICLR Conference 2022 Conference Paper

Learning a subspace of policies for online adaptation in Reinforcement Learning

Jean-Baptiste Gaya
Laure Soulier
Ludovic Denoyer

Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s) on which a policy is learned might differ from the robot(s) on which a policy will run. It can be caused by different internal factors (e.g., calibration issues, system attrition, defective modules) or also by external changes (e.g., weather conditions). There is a need to develop RL methods that generalize well to variations of the training conditions. In this article, we consider the simplest yet hard to tackle generalization setting where the test environment is unknown at train time, forcing the agent to adapt to the system's new dynamics. This online adaptation process can be computationally expensive (e.g., fine-tuning) and cannot rely on meta-RL techniques since there is just a single train environment. To do so, we propose an approach where we learn a subspace of policies within the parameter space. This subspace contains an infinite number of policies that are trained to solve the training environment while having different parameter values. As a consequence, two policies in that subspace process information differently and exhibit different behaviors when facing variations of the train environment. Our experiments carried out over a large variety of benchmarks compare our approach with baselines, including diversity-based methods. In comparison, our approach is simple to tune, does not need any extra component (e.g., discriminator) and learns policies able to gather a high reward on unseen environments.

Details

UAI Conference 2022 Conference Paper

Temporal abstractions-augmented temporally contrastive learning: An alternative to the Laplacian in RL

Akram Erraqabi
Marlos C. Machado
Mingde Zhao 0001
Sainbayar Sukhbaatar
Alessandro Lazaric
Ludovic Denoyer
Yoshua Bengio

In reinforcement learning, the graph Laplacian has proved to be a valuable tool in the task-agnostic setting, with applications ranging from skill discovery to reward shaping. Recently, learning the Laplacian representation has been framed as the optimization of a temporally-contrastive objective to overcome its computational limitations in large (or continuous) state spaces. However, this approach requires uniform access to all states in the state space, overlooking the exploration problem that emerges during the representation learning process. In this work, we propose an alternative method that is able to recover, in a non-uniform-prior setting, the expressiveness and the desired properties of the Laplacian representation. We do so by combining the representation learning with a skill-based covering policy, which provides a better training distribution to extend and refine the representation. We also show that a simple augmentation of the representation objective with the learned temporal abstractions improves dynamics-awareness and helps exploration. We find that our method succeeds as an alternative to the Laplacian in the non-uniform setting and scales to challenging continuous control environments. Finally, even if our method is not optimized for skill discovery, the learned skills can successfully solve difficult continuous navigation tasks with sparse rewards, where standard skill discovery approaches are no so effective.

Details

ICLR Conference 2021 Conference Paper

Efficient Continual Learning with Modular Networks and Task-Driven Priors

Tom Veniat
Ludovic Denoyer
Marc'Aurelio Ranzato

Existing literature in Continual Learning (CL) has focused on overcoming catastrophic forgetting, the inability of the learner to recall how to perform tasks observed in the past. There are however other desirable properties of a CL system, such as the ability to transfer knowledge from previous tasks and to scale memory and compute sub-linearly with the number of tasks. Since most current benchmarks focus only on forgetting using short streams of tasks, we first propose a new suite of benchmarks to probe CL algorithms across these new axes. Finally, we introduce a new modular architecture, whose modules represent atomic skills that can be composed to perform a certain task. Learning a task reduces to figuring out which past modules to re-use, and which new modules to instantiate to solve the current task. Our learning algorithm leverages a task-driven prior over the exponential search space of all possible ways to combine modules, enabling efficient learning on long streams of tasks. Our experiments show that this modular architecture and learning algorithm perform competitively on widely used CL benchmarks while yielding superior performance on the more challenging benchmarks we introduce in this work. The Benchmark is publicly available at https://github.com/facebookresearch/CTrLBenchmark.

Details

NeurIPS Conference 2019 Conference Paper

Large Memory Layers with Product Keys

Guillaume Lample
Alexandre Sablayrolles
Marc'Aurelio Ranzato
Ludovic Denoyer
Herve Jegou

This paper introduces a structured memory which can be easily integrated into a neural network. The memory is very large by design and significantly increases the capacity of the architecture, by up to a billion parameters with a negligible computational overhead. Its design and access pattern is based on product keys, which enable fast and exact nearest neighbor search. The ability to increase the number of parameters while keeping the same computational budget lets the overall system strike a better trade-off between prediction accuracy and computation efficiency both at training and test time. This memory layer allows us to tackle very large scale language modeling tasks. In our experiments we consider a dataset with up to 30 billion words, and we plug our memory layer in a state-of-the-art transformer-based architecture. In particular, we found that a memory augmented model with only 12 layers outperforms a baseline transformer model with 24 layers, while being twice faster at inference time. We release our code for reproducibility purposes.

PDF Details

NeurIPS Conference 2019 Conference Paper

Unsupervised Object Segmentation by Redrawing

Mickaël Chen
Thierry Artières
Ludovic Denoyer

Object segmentation is a crucial problem that is usually solved by using supervised learning approaches over very large datasets composed of both images and corresponding object masks. Since the masks have to be provided at pixel level, building such a dataset for any new domain can be very costly. We present ReDO, a new model able to extract objects from images without any annotation in an unsupervised way. It relies on the idea that it should be possible to change the textures or colors of the objects without changing the overall distribution of the dataset. Following this assumption, our approach is based on an adversarial architecture where the generator is guided by an input sample: given an image, it extracts the object mask, then redraws a new object at the same location. The generator is controlled by a discriminator that ensures that the distribution of generated images is aligned to the original one. We experiment with this method on different datasets and demonstrate the good quality of extracted masks.

PDF Details

NeurIPS Conference 2017 Conference Paper

Fader Networks:Manipulating Images by Sliding Attributes

Guillaume Lample
Neil Zeghidour
Nicolas Usunier
Antoine Bordes
Ludovic Denoyer
Marc'Aurelio Ranzato

This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space. As a result, after training, our model can generate different realistic versions of an input image by varying the attribute values. By using continuous attribute values, we can choose how much a specific attribute is perceivable in the generated image. This property could allow for applications where users can modify an image using sliding knobs, like faders on a mixing console, to change the facial expression of a portrait, or to update the color of some objects. Compared to the state-of-the-art which mostly relies on training adversarial networks in pixel space by altering attribute values at train time, our approach results in much simpler training schemes and nicely scales to multiple attributes. We present evidence that our model can significantly change the perceived value of the attributes while preserving the naturalness of images.

PDF Details

EWRL Workshop 2015 Workshop Paper

Deep Sequential Neural Networks

Ludovic Denoyer
Patrick Gallinari

Neural Networks sequentially build high-level features through their successive layers. We propose a new neural network model where each layer is associated with a set of candidate mappings. When an input is processed, at each layer, one mapping among these candidates is selected according to a sequential decision process. The resulting model is structured according to a DAG like architecture, so that a path from the root to a leaf node defines a sequence of transformations. The model is thus able to process data with different characteristics through specific sequences of local transformations, increasing the expression power of this model w.r.t a classical deep neural network. The learning algorithm is inspired from policy gradient techniques coming from the reinforcement learning domain and is used here instead of the classical back-propagation based gradient descent techniques.

Details

EWRL Workshop 2015 Workshop Paper

Reinforced Decision Trees

Aurélia Léon
Ludovic Denoyer

In order to speed-up classification models when facing a large number of categories, one usual approach consists in organizing the categories in a particular structure, this structure being then used as a way to speed-up the prediction computation. This is for example the case when using error-correcting codes or even hierarchies of categories. But in the majority of approaches, this structure is chosen by hand, or during a preliminary step, and not integrated in the learning process. We propose a new model called Reinforced Decision Tree which simultaneously learns how to organize categories in a tree structure and how to classify any input based on this structure. This approach keeps the advantages of existing techniques (low inference complexity) but allows one to build efficient classifiers in one learning step. The learning algorithm is inspired by reinforcement learning and policy-gradient techniques which allows us to integrate the two steps (building the tree, and learning the classifier) in one single algorithm.

Details

ICLR Conference 2014 Conference Paper

Sequentially Generated Instance-Dependent Image Representations for Classification

Gabriel Dulac-Arnold
Ludovic Denoyer
Nicolas Thome
Matthieu Cord
Patrick Gallinari

In this paper, we investigate a new framework for image classification that adaptively generates spatial representations. Our strategy is based on a sequential process that learns to explore the different regions of any image in order to infer its category. In particular, the choice of regions is specific to each image, directed by the actual content of previously selected regions.The capacity of the system to handle incomplete image information as well as its adaptive region selection allow the system to perform well in budgeted classification tasks by exploiting a dynamicly generated representation of each image. We demonstrate the system's abilities in a series of image-based exploration and classification tasks that highlight its learned exploration and inference abilities.

Details

EWRL Workshop 2008 Conference Paper

Applications of Reinforcement Learning to Structured Prediction

Francis Maes
Ludovic Denoyer
Patrick Gallinari

Abstract Supervised learning is about learning functions given a set of input and corresponding output examples. A recent trend in this field is to consider structured outputs such as sequences, trees or graphs. When predicting such structured data, learning models have to select solutions within very large discrete spaces. The combinatorial nature of this problem has recently led to learning models integrating a search component. In this paper, we show that Structured Prediction (SP) can be seen as a sequential decision problem. We introduce SP-MDP: a Markov Decision Process based formulation of Structured Prediction. Learning the optimal policy in SP-MDP is shown to be equivalent as solving the SP problem. This allows us to apply classical Reinforcement Learning (RL) algorithms to SP. We present experiments on two tasks. The first, sequence labeling, has been extensively studied and allows us to compare the RL approach with traditional SP methods. The second, tree transformation, is a challenging SP task with numerous large-scale real-world applications. We show successful results with general RL algorithms on this task on which traditional SP models fail.

Details