Search Results for author: Rémi Munos

Found 77 papers, 19 papers with code

Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model

no code implementations12 Feb 2024 Mark Rowland, Li Kevin Wenliang, Rémi Munos, Clare Lyle, Yunhao Tang, Will Dabney

We propose a new algorithm for model-based distributional reinforcement learning (RL), and prove that it is minimax-optimal for approximating return distributions with a generative model (up to logarithmic factors), resolving an open question of Zhang et al. (2023).

Distributional Reinforcement Learning reinforcement-learning +1

Off-policy Distributional Q($λ$): Distributional RL without Importance Sampling

no code implementations8 Feb 2024 Yunhao Tang, Mark Rowland, Rémi Munos, Bernardo Ávila Pires, Will Dabney

We introduce off-policy distributional Q($\lambda$), a new addition to the family of off-policy distributional evaluation algorithms.

Generalized Preference Optimization: A Unified Approach to Offline Alignment

no code implementations8 Feb 2024 Yunhao Tang, Zhaohan Daniel Guo, Zeyu Zheng, Daniele Calandriello, Rémi Munos, Mark Rowland, Pierre Harvey Richemond, Michal Valko, Bernardo Ávila Pires, Bilal Piot

Offline preference optimization allows fine-tuning large models directly from offline data, and has proved effective in recent alignment practices.

A General Theoretical Paradigm to Understand Learning from Human Preferences

1 code implementation18 Oct 2023 Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot, Daniel Guo, Daniele Calandriello, Michal Valko, Rémi Munos

In particular we derive a new general objective called $\Psi$PO for learning from human preferences that is expressed in terms of pairwise preferences and therefore bypasses both approximations.

Local and adaptive mirror descents in extensive-form games

no code implementations1 Sep 2023 Côme Fiegel, Pierre Ménard, Tadashi Kozuno, Rémi Munos, Vianney Perchet, Michal Valko

We study how to learn $\epsilon$-optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback.

VA-learning as a more efficient alternative to Q-learning

no code implementations29 May 2023 Yunhao Tang, Rémi Munos, Mark Rowland, Michal Valko

In reinforcement learning, the advantage function is critical for policy improvement, but is often extracted from a learned Q-function.

Q-Learning

DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm

no code implementations29 May 2023 Yunhao Tang, Tadashi Kozuno, Mark Rowland, Anna Harutyunyan, Rémi Munos, Bernardo Ávila Pires, Michal Valko

Multi-step learning applies lookahead over multiple time steps and has proved valuable in policy evaluation settings.

Towards a Better Understanding of Representation Dynamics under TD-learning

no code implementations29 May 2023 Yunhao Tang, Rémi Munos

Complementary to prior work, we provide a set of analysis that sheds further light on the representation dynamics under TD-learning.

Reinforcement Learning (RL) Representation Learning +1

An Analysis of Quantile Temporal-Difference Learning

no code implementations11 Jan 2023 Mark Rowland, Rémi Munos, Mohammad Gheshlaghi Azar, Yunhao Tang, Georg Ostrovski, Anna Harutyunyan, Karl Tuyls, Marc G. Bellemare, Will Dabney

We analyse quantile temporal-difference learning (QTD), a distributional reinforcement learning algorithm that has proven to be a key component in several successful large-scale applications of reinforcement learning.

Distributional Reinforcement Learning reinforcement-learning +1

Adapting to game trees in zero-sum imperfect information games

1 code implementation23 Dec 2022 Côme Fiegel, Pierre Ménard, Tadashi Kozuno, Rémi Munos, Vianney Perchet, Michal Valko

Imperfect information games (IIG) are games in which each player only partially observes the current game state.

Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments

no code implementations18 Nov 2022 Daniel Jarrett, Corentin Tallec, Florent Altché, Thomas Mesnard, Rémi Munos, Michal Valko

In this work, we study a natural solution derived from structural causal models of the world: Our key idea is to learn representations of the future that capture precisely the unpredictable aspects of each outcome -- which we use as additional input for predictions, such that intrinsic rewards only reflect the predictable aspects of world dynamics.

Montezuma's Revenge

Generalised Policy Improvement with Geometric Policy Composition

no code implementations17 Jun 2022 Shantanu Thakoor, Mark Rowland, Diana Borsa, Will Dabney, Rémi Munos, André Barreto

We introduce a method for policy improvement that interpolates between the greedy approach of value-based reinforcement learning (RL) and the full planning approach typical of model-based RL.

Continuous Control Reinforcement Learning (RL)

Marginalized Operators for Off-policy Reinforcement Learning

no code implementations30 Mar 2022 Yunhao Tang, Mark Rowland, Rémi Munos, Michal Valko

We show that the estimates for marginalized operators can be computed in a scalable way, which also generalizes prior results on marginalized importance sampling as special cases.

Off-policy evaluation reinforcement-learning

Taylor Expansion of Discount Factors

no code implementations11 Jun 2021 Yunhao Tang, Mark Rowland, Rémi Munos, Michal Valko

In practical reinforcement learning (RL), the discount factor used for estimating value functions often differs from that used for defining the evaluation objective.

reinforcement-learning Reinforcement Learning (RL)

Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall

no code implementations11 Jun 2021 Tadashi Kozuno, Pierre Ménard, Rémi Munos, Michal Valko

We study the problem of learning a Nash equilibrium (NE) in an imperfect information game (IIG) through self-play.

Revisiting Peng's Q($λ$) for Modern Reinforcement Learning

no code implementations27 Feb 2021 Tadashi Kozuno, Yunhao Tang, Mark Rowland, Rémi Munos, Steven Kapturowski, Will Dabney, Michal Valko, David Abel

These results indicate that Peng's Q($\lambda$), which was thought to be unsafe, is a theoretically-sound and practically effective algorithm.

Continuous Control reinforcement-learning +1

Large-Scale Representation Learning on Graphs via Bootstrapping

3 code implementations ICLR 2022 Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, Mehdi Azabou, Eva L. Dyer, Rémi Munos, Petar Veličković, Michal Valko

To address these challenges, we introduce Bootstrapped Graph Latents (BGRL) - a graph representation learning method that learns by predicting alternative augmentations of the input.

Contrastive Learning Graph Representation Learning +1

Leverage the Average: an Analysis of KL Regularization in RL

no code implementations31 Mar 2020 Nino Vieillard, Tadashi Kozuno, Bruno Scherrer, Olivier Pietquin, Rémi Munos, Matthieu Geist

Recent Reinforcement Learning (RL) algorithms making use of Kullback-Leibler (KL) regularization as a core component have shown outstanding performance.

Reinforcement Learning (RL)

Adaptive Trade-Offs in Off-Policy Learning

no code implementations16 Oct 2019 Mark Rowland, Will Dabney, Rémi Munos

A great variety of off-policy learning algorithms exist in the literature, and new breakthroughs in this area continue to be made, improving theoretical understanding and yielding state-of-the-art reinforcement learning algorithms.

Off-policy evaluation reinforcement-learning

Towards Consistent Performance on Atari using Expert Demonstrations

no code implementations ICLR 2019 Tobias Pohlen, Bilal Piot, Todd Hester, Mohammad Gheshlaghi Azar, Dan Horgan, David Budden, Gabriel Barth-Maron, Hado van Hasselt, John Quan, Mel Večerík, Matteo Hessel, Rémi Munos, Olivier Pietquin

Despite significant advances in the field of deep Reinforcement Learning (RL), today's algorithms still fail to learn human-level policies consistently over a set of diverse tasks such as Atari 2600 games.

Atari Games Reinforcement Learning (RL)

Statistics and Samples in Distributional Reinforcement Learning

no code implementations21 Feb 2019 Mark Rowland, Robert Dadashi, Saurabh Kumar, Rémi Munos, Marc G. Bellemare, Will Dabney

We present a unifying framework for designing and analysing distributional reinforcement learning (DRL) algorithms in terms of recursively estimating statistics of the return distribution.

Distributional Reinforcement Learning reinforcement-learning +1

World Discovery Models

1 code implementation20 Feb 2019 Mohammad Gheshlaghi Azar, Bilal Piot, Bernardo Avila Pires, Jean-bastien Grill, Florent Altché, Rémi Munos

As humans we are driven by a strong desire for seeking novelty in our world.

Optimistic optimization of a Brownian

no code implementations NeurIPS 2018 Jean-bastien Grill, Michal Valko, Rémi Munos

Given $W$, our goal is to return an $\epsilon$-approximation of its maximum using the smallest possible number of function evaluations, the sample complexity of the algorithm.

Neural Predictive Belief Representations

no code implementations15 Nov 2018 Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Bernardo A. Pires, Rémi Munos

In partially observable domains it is important for the representation to encode a belief state, a sufficient statistic of the observations seen so far.

Decision Making Representation Learning

Implicit Quantile Networks for Distributional Reinforcement Learning

20 code implementations ICML 2018 Will Dabney, Georg Ostrovski, David Silver, Rémi Munos

In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN.

Atari Games Distributional Reinforcement Learning +3

Autoregressive Quantile Networks for Generative Modeling

1 code implementation ICML 2018 Georg Ostrovski, Will Dabney, Rémi Munos

We introduce autoregressive implicit quantile networks (AIQN), a fundamentally different approach to generative modeling than those commonly used, that implicitly captures the distribution using quantile regression.

regression

Observe and Look Further: Achieving Consistent Performance on Atari

no code implementations29 May 2018 Tobias Pohlen, Bilal Piot, Todd Hester, Mohammad Gheshlaghi Azar, Dan Horgan, David Budden, Gabriel Barth-Maron, Hado van Hasselt, John Quan, Mel Večerík, Matteo Hessel, Rémi Munos, Olivier Pietquin

Despite significant advances in the field of deep Reinforcement Learning (RL), today's algorithms still fail to learn human-level policies consistently over a set of diverse tasks such as Atari 2600 games.

Montezuma's Revenge Reinforcement Learning (RL)

An Analysis of Categorical Distributional Reinforcement Learning

no code implementations22 Feb 2018 Mark Rowland, Marc G. Bellemare, Will Dabney, Rémi Munos, Yee Whye Teh

Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yield state-of-the-art empirical performance.

Distributional Reinforcement Learning reinforcement-learning +1

Learning to Search with MCTSnets

2 code implementations ICML 2018 Arthur Guez, Théophane Weber, Ioannis Antonoglou, Karen Simonyan, Oriol Vinyals, Daan Wierstra, Rémi Munos, David Silver

They are most typically solved by tree search algorithms that simulate ahead into the future, evaluate future states, and back-up those evaluations to the root of a search tree.

Distributional Reinforcement Learning with Quantile Regression

17 code implementations27 Oct 2017 Will Dabney, Mark Rowland, Marc G. Bellemare, Rémi Munos

In this paper, we build on recent work advocating a distributional approach to reinforcement learning in which the distribution over returns is modeled explicitly instead of only estimating the mean.

Atari Games Distributional Reinforcement Learning +3

A Distributional Perspective on Reinforcement Learning

22 code implementations ICML 2017 Marc G. Bellemare, Will Dabney, Rémi Munos

We obtain both state-of-the-art results and anecdotal evidence demonstrating the importance of the value distribution in approximate reinforcement learning.

Atari Games reinforcement-learning +1

Observational Learning by Reinforcement Learning

no code implementations20 Jun 2017 Diana Borsa, Bilal Piot, Rémi Munos, Olivier Pietquin

Observational learning is a type of learning that occurs as a function of observing, retaining and possibly replicating or imitating the behaviour of another agent.

reinforcement-learning Reinforcement Learning (RL)

Increasing the Action Gap: New Operators for Reinforcement Learning

2 code implementations15 Dec 2015 Marc G. Bellemare, Georg Ostrovski, Arthur Guez, Philip S. Thomas, Rémi Munos

Extending the idea of a locally consistent operator, we then derive sufficient conditions for an operator to preserve optimality, leading to a family of operators which includes our consistent Bellman operator.

Atari Games Q-Learning +2

Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits

no code implementations16 Jul 2015 Alexandra Carpentier, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos, Peter Auer, András Antos

If the variance of the distributions were known, one could design an optimal sampling strategy by collecting a number of independent samples per distribution that is proportional to their variance.

Active Learning Multi-Armed Bandits

Best-Arm Identification in Linear Bandits

no code implementations NeurIPS 2014 Marta Soare, Alessandro Lazaric, Rémi Munos

We study the best-arm identification problem in linear bandit, where the rewards of the arms depend linearly on an unknown parameter $\theta^*$ and the objective is to return the arm with the largest reward.

Experimental Design

Fast gradient descent for drifting least squares regression, with application to bandits

no code implementations11 Jul 2013 Nathaniel Korda, Prashanth L. A., Rémi Munos

In the case when strong convexity in the regression problem is guaranteed, we provide bounds on the error both in expectation and high probability (the latter is often needed to provide theoretical guarantees for higher level algorithms), despite the drifting least squares solution.

News Recommendation regression

Concentration bounds for temporal difference learning with linear function approximation: The case of batch data and uniform sampling

no code implementations11 Jun 2013 L. A. Prashanth, Nathaniel Korda, Rémi Munos

We propose a stochastic approximation (SA) based method with randomization of samples for policy evaluation using the least squares temporal difference (LSTD) algorithm.

Multi-Armed Bandits News Recommendation +1

Risk-Aversion in Multi-armed Bandits

no code implementations NeurIPS 2012 Amir Sani, Alessandro Lazaric, Rémi Munos

In stochastic multi--armed bandits the objective is to solve the exploration--exploitation dilemma and ultimately maximize the expected reward.

Multi-Armed Bandits

Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions

no code implementations NeurIPS 2012 Alexandra Carpentier, Rémi Munos

We consider the problem of adaptive stratified sampling for Monte Carlo integration of a differentiable function given a finite number of evaluations to the function.

Thompson Sampling: An Asymptotically Optimal Finite Time Analysis

1 code implementation18 May 2012 Emilie Kaufmann, Nathaniel Korda, Rémi Munos

The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933.

3D Reconstruction Thompson Sampling

Speedy Q-Learning

no code implementations NeurIPS 2011 Mohammad Ghavamzadeh, Hilbert J. Kappen, Mohammad G. Azar, Rémi Munos

We introduce a new convergent variant of Q-learning, called speedy Q-learning, to address the problem of slow convergence in the standard form of the Q-learning algorithm.

Q-Learning

Selecting the State-Representation in Reinforcement Learning

no code implementations NeurIPS 2011 Odalric-Ambrym Maillard, Daniil Ryabko, Rémi Munos

Without knowing neither which of the models is the correct one, nor what are the probabilistic characteristics of the resulting MDP, it is required to obtain as much reward as the optimal policy for the correct model (or for the best of the correct models, if there are several).

reinforcement-learning Reinforcement Learning (RL)

Sparse Recovery with Brownian Sensing

no code implementations NeurIPS 2011 Alexandra Carpentier, Odalric-Ambrym Maillard, Rémi Munos

We consider the problem of recovering the parameter alpha in R^K of a sparse function f, i. e. the number of non-zero entries of alpha is small compared to the number K of features, given noisy evaluations of f at a set of well-chosen sampling points.

Scrambled Objects for Least-Squares Regression

no code implementations NeurIPS 2010 Odalric Maillard, Rémi Munos

We consider least-squares regression using a randomly generated subspace G_P\subset F of finite dimension P, where F is a function space of infinite dimension, e. g.~L_2([0, 1]^d).

regression

Error Propagation for Approximate Policy and Value Iteration

no code implementations NeurIPS 2010 Amir-Massoud Farahmand, Csaba Szepesvári, Rémi Munos

We address the question of how the approximation error/Bellman residual at each iteration of the Approximate Policy/Value Iteration algorithms influences the quality of the resulted policy.

LSTD with Random Projections

no code implementations NeurIPS 2010 Mohammad Ghavamzadeh, Alessandro Lazaric, Odalric Maillard, Rémi Munos

We provide a thorough theoretical analysis of the LSTD with random projections and derive performance bounds for the resulting algorithm.

reinforcement-learning Reinforcement Learning (RL)

Sensitivity analysis in HMMs with application to likelihood maximization

no code implementations NeurIPS 2009 Pierre-Arnaud Coquelin, Romain Deguest, Rémi Munos

We derive an IPA estimator for the gradient of the log-likelihood, which may be used in a gradient method for the purpose of likelihood maximization.

Compressed Least-Squares Regression

no code implementations NeurIPS 2009 Odalric Maillard, Rémi Munos

We consider the problem of learning, from K input data, a regression function in a function space of high dimension N using projections onto a random subspace of lower dimension M. From any linear approximation algorithm using empirical risk minimization (possibly penalized), we provide bounds on the excess risk of the estimate computed in the projected subspace (compressed domain) in terms of the excess risk of the estimate built in the high-dimensional space (initial domain).

regression

Online Optimization in X-Armed Bandits

no code implementations NeurIPS 2008 Sébastien Bubeck, Gilles Stoltz, Csaba Szepesvári, Rémi Munos

We consider a generalization of stochastic bandit problems where the set of arms, X, is allowed to be a generic topological space.

Particle Filter-based Policy Gradient in POMDPs

no code implementations NeurIPS 2008 Pierre-Arnaud Coquelin, Romain Deguest, Rémi Munos

Our setting is a Partially Observable Markov Decision Process with continuous state, observation and action spaces.

Algorithms for Infinitely Many-Armed Bandits

no code implementations NeurIPS 2008 Yizao Wang, Jean-Yves Audibert, Rémi Munos

We consider multi-armed bandit problems where the number of arms is larger than the possible number of experiments.

Fitted Q-iteration in continuous action-space MDPs

no code implementations NeurIPS 2007 András Antos, Csaba Szepesvári, Rémi Munos

We consider continuous state, continuous action batch reinforcement learning where the goal is to learn a good policy from a sufficiently rich trajectory generated by another policy.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.