Search Results for author:
Found 33 papers, 6 papers with code
PAQA: Toward ProActive Open-Retrieval Question Answering
Conversational systems have made significant progress in generating natural language responses.
Augmenting Ad-Hoc IR Dataset for Interactive Conversational Search
The only two datasets known to us that contain both document relevance judgments and the associated clarification interactions are Qulac and ClariQ.
Limits of Actor-Critic Algorithms for Decision Tree Policies Learning in IBMDPs
We show in this paper that deep RL can fail even on simple toy tasks of this class.
Interpretable Decision Tree Search as a Markov Decision Process
Finding an optimal decision tree for a supervised learning task is a challenging combinatorial problem to solve at scale.
Development and validation of an interpretable machine learning-based calculator for predicting 5-year weight trajectories after bariatric surgery: a multinational retrospective cohort SOPHIA study
We aimed to develop a model using machine learning to provide individual preoperative prediction of 5-year weight loss trajectories after surgery.
AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents
When comparing several RL algorithms, a major question is how many executions must be made and how can we ensure that the results of such a comparison are theoretically sound.
Optimal Interpretability-Performance Trade-off of Classification Trees with Black-Box Reinforcement Learning
A given supervised classification task is modeled as a Markov decision problem (MDP) and then augmented with additional actions that gather information about the features, equivalent to building a DT.
Entropy Regularized Reinforcement Learning with Cascading Networks
Compared to these learning frameworks, one of the major difficulties of RL is the absence of i. i. d.
Soft Action Priors: Towards Robust Policy Transfer
Despite success in many challenging problems, reinforcement learning (RL) is still confronted with sample inefficiency, which can be mitigated by introducing prior knowledge to agents.
gym-DSSAT: a crop model turned into a Reinforcement Learning environment
gym-DSSAT is a gym interface to the Decision Support System for Agrotechnology Transfer (DSSAT), a high fidelity crop simulator.
More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences
Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question.
Better state exploration using action sequence equivalence
Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question.
There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning
We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL).
Interferometric Graph Transform for Community Labeling
We present a new approach for learning unsupervised node representations in community graphs.
Low-Rank Projections of GCNs Laplacian
In this work, we study the behavior of standard models for community detection under spectral manipulations.
Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness
Sparse rewards are double-edged training signals in reinforcement learning: easy to design but hard to optimize.
Relevant Action Matters : Motivating agent with action usefulness
We evaluate RAM on the procedurally-generated environment MiniGrid, against state-of-the-art methods.
Adversarially Guided Actor-Critic
Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bottleneck.
A spectral perspective on GCNs
In this work, we study the behavior of standard GCNs under spectral manipulations.
Geometric Deep Reinforcement Learning for Dynamic DAG Scheduling
In this paper, we propose a reinforcement learning approach to solve a realistic scheduling problem, and apply it to an algorithm commonly executed in the high performance computing community, the Cholesky factorization.
Learning Value Functions in Deep Policy Gradients using Residual Variance
We prove the theoretical consistency of the new gradient estimator and observe dramatic empirical improvement across a variety of continuous control tasks and algorithms.
A Machine of Few Words -- Interactive Speaker Recognition with Reinforcement Learning
To do so, we cast the speaker recognition task into a sequential decision-making problem that we solve with Reinforcement Learning.
I'm sorry Dave, I'm afraid I can't do that, Deep Q-learning from forbidden action
Violating constraints thus results in rejected actions or entering in a safe mode driven by an external controller, making RL agents incapable of learning from their mistakes.
MERL: Multi-Head Reinforcement Learning
In this paper: (a) We introduce and define MERL, the multi-head reinforcement learning framework we use throughout this work.
Samples Are Useful? Not Always: denoising policy gradient updates using variance explained
In this work, Vex is used to evaluate the impact each transition will have on learning: this criterion refines sampling and improves the policy gradient algorithm.
Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL
In this work, we use this metric to select samples that are useful to learn from, and we demonstrate that this selection can significantly improve the performance of policy gradient methods.
Visual Reasoning with Multi-hop Feature Modulation
Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue.
Recurrent Neural Networks for Long and Short-Term Sequential Recommendation
Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon.
Operator-valued Kernels for Learning from Functional Response Data
In this paper we consider the problems of supervised classification and regression in the case where attributes and labels are functions: a data is represented by a set of functions, and the label is also a function.
A Generative Model of Software Dependency Graphs to Better Understand Software Evolution
Then, we propose a generative model of software dependency graphs which synthesizes graphs whose degree distribution is close to the empirical ones observed in real software systems.
Software Engineering
Improving offline evaluation of contextual bandit algorithms via bootstrapping techniques
In general the evaluation of a RS is a critical issue.
Multiple Operator-valued Kernel Learning
We study this problem in the case of kernel ridge regression for functional responses with an lr-norm constraint on the combination coefficients.
A Generalized Kernel Approach to Structured Output Learning
Finally, we evaluate the performance of our KDE approach using both covariance and conditional covariance kernels on two structured output problems, and compare it to the state-of-the-art kernel-based structured output regression methods.
