Nicolas Le Roux

NeurIPS Conference 2025 Conference Paper

Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models

• Nicolas Le Roux
• Marc Bellemare
• Jonathan Lebensold
• Arnaud Bergeron
• Joshua Greaves
• Alexandre Fréchette
• Carolyne Pelletier
• Eric Thibodeau-Laufer

We propose a new algorithm for fine-tuning large language models using reinforcement learning. Tapered Off-Policy REINFORCE (TOPR) uses an asymmetric, tapered variant of importance sampling to speed up learning while maintaining stable learning dynamics, even without the use of KL regularization. TOPR can be applied in a fully offline fashion, allows the handling of positive and negative examples in a unified framework, and benefits from the implementational simplicity that is typical of Monte Carlo algorithms. We demonstrate the effectiveness of our approach with a series of experiments on the GSM8K and MATH reasoning benchmarks, finding performance gains for training both a model for solution generation and as a generative verifier. We show that properly leveraging positive and negative examples alike in the off-policy regime simultaneously increases test-time accuracy and training data efficiency, all the while avoiding the ``wasted inference'' that comes with discarding negative examples. We find that this advantage persists over multiple iterations of training and can be amplified by dataset curation techniques, enabling us to match 70B-parameter model performance with 8B language models. As a corollary to this work, we find that REINFORCE's baseline parameter plays an important and unexpected role in defining dataset composition in the presence of negative examples, and is consequently critical in driving off-policy performance.

ICML Conference 2025 Conference Paper

VinePPO: Refining Credit Assignment in RL Training of LLMs

• Amirhossein Kazemnejad
• Milad Aghajohari
• Eva Portelance
• Alessandro Sordoni
• Siva Reddy
• Aaron C. Courville
• Nicolas Le Roux

Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit to these steps is essential for enhancing model performance. Proximal Policy Optimization (PPO), a common reinforcement learning (RL) algorithm used for LLM finetuning, employs value networks to tackle credit assignment. However, recent approaches achieve strong results without it, raising questions about the efficacy of value networks in practice. In this work, we systematically evaluate the efficacy of value networks and reveal their significant shortcomings in reasoning-heavy LLM tasks, showing that they often produce poor estimate of expected return and barely outperform a random baseline when comparing alternative steps. This motivates our key question: Can improved credit assignment enhance RL training for LLMs? To address this, we propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates. Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time (up to 3. 0x). Crucially, it achieves higher test accuracy for a given training accuracy, capturing more generalization signal per sample. These results emphasize the importance of accurate credit assignment in RL training of LLM.

NeurIPS Conference 2024 Conference Paper

Improving Context-Aware Preference Modeling for Language Models

• Silviu Pitis
• Ziang Xiao
• Nicolas Le Roux
• Alessandro Sordoni

While finetuning language models from pairwise preferences has proven remarkably effective, the underspecified nature of natural language presents critical challenges. Direct preference feedback is uninterpretable, difficult to provide where multidimensional criteria may apply, and often inconsistent, either because it is based on incomplete instructions or provided by diverse principals. To address these challenges, we consider the two-step preference modeling procedure that first resolves the under-specification by selecting a context, and then evaluates preference with respect to the chosen context. We decompose reward modeling error according to these two steps, which suggests that supervising context in addition to context-specific preference may be a viable approach to aligning models with diverse human preferences. For this to work, the ability of models to evaluate context-specific preference is critical. To this end, we contribute context-conditioned preference datasets and accompanying experiments that investigate the ability of language models to evaluate context-specific preference. Unlike past datasets, where context-specific preference is highly correlated with general preference, our "preference reversal" datasets disentangle context-specific and general preferences to isolate context-specific capabilities. We use our datasets to (1) show that existing preference models benefit from, but fail to fully consider, added context, (2) finetune a context-aware reward model with context-specific performance exceeding that of GPT-4 and Llama 3 70B, and (3) investigate the potential value of context-aware preference modeling.

ICML Conference 2024 Conference Paper

Language-guided Skill Learning with Temporal Variational Inference

• Haotian Fu
• Pratyusha Sharma
• Elias Stengel-Eskin
• George Konidaris 0001
• Nicolas Le Roux
• Marc-Alexandre Côté
• Xingdi Yuan

We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical variational inference framework incorporates the LLM-generated segmentation information to discover reusable skills by merging trajectory segments. To further control the trade-off between compression and reusability, we introduce a novel auxiliary objective based on the Minimum Description Length principle that helps guide this skill discovery process. Our results demonstrate that agents equipped with our method are able to discover skills that help accelerate learning and outperform baseline skill learning approaches on new long-horizon tasks in BabyAI, a grid world navigation environment, as well as ALFRED, a household simulation environment.

ICML Conference 2024 Conference Paper

Towards Modular LLMs by Building and Reusing a Library of LoRAs

• Oleksiy Ostapenko
• Zhan Su 0002
• Edoardo M. Ponti
• Laurent Charlin
• Nicolas Le Roux
• Lucas Caccia
• Alessandro Sordoni

Given the increasing number of parameter-efficient adapters of large language models (LLMs), how can we reuse them to improve LLM performance on new tasks? We study how to best build a library of adapters given multi-task data and devise techniques for both zero-shot and supervised task generalization through routing in such library. We benchmark existing approaches to build this library and introduce model-based clustering, $\texttt{MBC}$, a method that groups tasks based on the similarity of their adapter parameters, indirectly optimizing for transfer across the multi-task dataset. In order to reuse the library, we present a novel zero-shot routing mechanism, $\texttt{Arrow}$, which enables dynamic selection of the most relevant adapters for new inputs without the need for retraining. We experiment with several LLMs, such as Phi-2 and Mistral, on a wide array of held-out tasks, verifying that MBC-based adapters and Arrow routing lead to superior generalization to new tasks. Thus, we make steps towards creating modular, adaptable LLMs that can match or outperform traditional joint training.

NeurIPS Conference 2023 Conference Paper

Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees

• Sharan Vaswani
• Amirreza Kazemi
• Reza Babanezhad Harikandeh
• Nicolas Le Roux

Actor-critic (AC) methods are widely used in reinforcement learning (RL), and benefit from the flexibility of using any policy gradient method as the actor and value-based method as the critic. The critic is usually trained by minimizing the TD error, an objective that is potentially decorrelated with the true goal of achieving a high reward with the actor. We address this mismatch by designing a joint objective for training the actor and critic in a decision-aware fashion. We use the proposed objective to design a generic, AC algorithm that can easily handle any function approximation. We explicitly characterize the conditions under which the resulting algorithm guarantees monotonic policy improvement, regardless of the choice of the policy and critic parameterization. Instantiating the generic algorithm results in an actor that involves maximizing a sequence of surrogate functions (similar to TRPO, PPO), and a critic that involves minimizing a closely connected objective. Using simple bandit examples, we provably establish the benefit of the proposed critic objective over the standard squared error. Finally, we empirically demonstrate the benefit of our decision-aware actor-critic framework on simple RL problems.

NeurIPS Conference 2023 Conference Paper

Joint Prompt Optimization of Stacked LLMs using Variational Inference

• Alessandro Sordoni
• Eric Yuan
• Marc-Alexandre Côté
• Matheus Pereira
• Adam Trischler
• Ziang Xiao
• Arian Hosseini
• Friederike Niedtner

Large language models (LLMs) can be seen as atomic units of computation mapping sequences to a distribution over sequences. Thus, they can be seen as stochastic language layers in a language network, where the learnable parameters are the natural language prompts at each layer. By stacking two such layers and feeding the output of one layer to the next, we obtain a Deep Language Network (DLN). We first show how to effectively perform prompt optimization for a 1-Layer language network (DLN-1). Then, we present an extension that applies to 2-layer DLNs (DLN-2), where two prompts must be learned. The key idea is to consider the output of the first layer as a latent variable, which requires inference, and prompts to be learned as the parameters of the generative distribution. We first test the effectiveness of DLN-1 in multiple reasoning and natural language understanding tasks. Then, we show that DLN-2 can reach higher performance than a single layer, showing promise that we might reach comparable performance to GPT-4, even when each LLM in the network is smaller and less powerful.

NeurIPS Conference 2023 Conference Paper

Multi-Head Adapter Routing for Cross-Task Generalization

• Lucas Page-Caccia
• Edoardo Maria Ponti
• Zhan Su
• Matheus Pereira
• Nicolas Le Roux
• Alessandro Sordoni

Parameter-efficient fine-tuning (PEFT) for cross-task generalization consists in pre-training adapters on a multi-task training set before few-shot adaptation to test tasks. Polytropon [Ponti et al. , 2023] ($\texttt{Poly}$) jointly learns an inventory of adapters and a *routing* function that selects a (variable-size) subset of adapters for each task during both pre-training and few-shot adaptation. In this paper, we investigate the role that adapter routing plays in its success and design new variants based on our findings. First, we build on the intuition that finer-grained routing provides more expressivity. Hence, we propose $\texttt{MHR}$ (Multi-Head Routing) which combines *subsets* of adapter parameters and outperforms $\texttt{Poly}$ under a comparable parameter budget; by only fine-tuning the routing function and not the adapters ($\texttt{MHR}$-$z$) we achieve competitive performance with extreme parameter efficiency. Second, we find that $\texttt{Poly}$/$\texttt{MHR}$ performance is a result of better multi-task optimization, rather than modular inductive biases that facilitate adapter recombination and local adaptation, as previously hypothesized. In fact, we find that $\texttt{MHR}$ exhibits high gradient alignment between training tasks. We find that routing is most beneficial during multi-task pre-training rather than during few-shot adaptation and propose $\texttt{MHR}$-$\mu$, which discards routing and fine-tunes the average of the pre-trained adapters on each downstream tasks. This establishes $\texttt{MHR}$-$\mu$ as an effective method for single-adapter fine-tuning. We also show that $\texttt{MHR}$-$\mu$ can be used as an effective zero-shot transfer method by training the average of the pre-trained adapters for a few additional steps on the multi-task training set: this yields gains up to 3\% on absolute accuracy w. r. t. the baselines. Code is available at.

ICML Conference 2023 Conference Paper

Target-based Surrogates for Stochastic Optimization

• Jonathan Wilder Lavington
• Sharan Vaswani
• Reza Babanezhad 0001
• Mark Schmidt 0001
• Nicolas Le Roux

We consider minimizing functions for which it is expensive to compute the (possibly stochastic) gradient. Such functions are prevalent in reinforcement learning, imitation learning and adversarial training. Our target optimization framework uses the (expensive) gradient computation to construct surrogate functions in a target space (e. g. the logits output by a linear model for classification) that can be minimized efficiently. This allows for multiple parameter updates to the model, amortizing the cost of gradient computation. In the full-batch setting, we prove that our surrogate is a global upper-bound on the loss, and can be (locally) minimized using a black-box optimization algorithm. We prove that the resulting majorization-minimization algorithm ensures convergence to a stationary point of the loss. Next, we instantiate our framework in the stochastic setting and propose the $SSO$ algorithm, which can be viewed as projected stochastic gradient descent in the target space. This connection enables us to prove theoretical guarantees for $SSO$ when minimizing convex functions. Our framework allows the use of standard stochastic optimization algorithms to construct surrogates which can be minimized by any deterministic optimization method. To evaluate our framework, we consider a suite of supervised learning and imitation learning problems. Our experiments indicate the benefits of target optimization and the effectiveness of $SSO$.

ICLR Conference 2021 Conference Paper

Batch Reinforcement Learning Through Continuation Method

• Yijie Guo
• Shengyu Feng
• Nicolas Le Roux
• Ed H. Chi
• Honglak Lee
• Minmin Chen

Many real-world applications of reinforcement learning (RL) require the agent to learn from a fixed set of trajectories, without collecting new interactions. Policy optimization under this setting is extremely challenging as: 1) the geometry of the objective function is hard to optimize efficiently; 2) the shift of data distributions causes high noise in the value estimation. In this work, we propose a simple yet effective policy iteration approach to batch RL using global optimization techniques known as continuation. By constraining the difference between the learned policy and the behavior policy that generates the fixed trajectories, and continuously relaxing the constraint, our method 1) helps the agent escape local optima; 2) reduces the error in policy evaluation in the optimization procedure. We present results on a variety of control tasks, game environments, and a recommendation task to empirically demonstrate the efficacy of our proposed method.

ICML Conference 2021 Conference Paper

Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization

• Wesley Chung
• Valentin Thomas
• Marlos C. Machado
• Nicolas Le Roux

Bandit and reinforcement learning (RL) problems can often be framed as optimization problems where the goal is to maximize average performance while having access only to stochastic estimates of the true gradient. Traditionally, stochastic optimization theory predicts that learning dynamics are governed by the curvature of the loss function and the noise of the gradient estimates. In this paper we demonstrate that the standard view is too limited for bandit and RL problems. To allow our analysis to be interpreted in light of multi-step MDPs, we focus on techniques derived from stochastic optimization principles (e. g. , natural policy gradient and EXP3) and we show that some standard assumptions from optimization theory are violated in these problems. We present theoretical results showing that, at least for bandit problems, curvature and noise are not sufficient to explain the learning dynamics and that seemingly innocuous choices like the baseline can determine whether an algorithm converges. These theoretical findings match our empirical evaluation, which we extend to multi-state MDPs.

NeurIPS Conference 2020 Conference Paper

An operator view of policy gradient methods

• Dibya Ghosh
• Marlos C. Machado
• Nicolas Le Roux

We cast policy gradient methods as the repeated application of two operators: a policy improvement operator $\mathcal{I}$, which maps any policy $\pi$ to a better one $\mathcal{I}\pi$, and a projection operator $\mathcal{P}$, which finds the best approximation of $\mathcal{I}\pi$ in the set of realizable policies. We use this framework to introduce operator-based versions of well-known policy gradient methods such as REINFORCE and PPO, which leads to a better understanding of their original counterparts. We also use the understanding we develop of the role of $\mathcal{I}$ and $\mathcal{P}$ to propose a new global lower bound of the expected return. This new perspective allows us to further bridge the gap between policy-based and value-based methods, showing how REINFORCE and the Bellman optimality operator, for example, can be seen as two sides of the same coin.

NeurIPS Conference 2019 Conference Paper

A Geometric Perspective on Optimal Representations for Reinforcement Learning

• Marc Bellemare
• Will Dabney
• Robert Dadashi
• Adrien Ali Taiga
• Pablo Samuel Castro
• Nicolas Le Roux
• Dale Schuurmans
• Tor Lattimore

We propose a new perspective on representation learning in reinforcement learning based on geometric properties of the space of value functions. From there, we provide formal evidence regarding the usefulness of value functions as auxiliary tasks in reinforcement learning. Our formulation considers adapting the representation to minimize the (linear) approximation of the value function of all stationary policies for a given environment. We show that this optimization reduces to making accurate predictions regarding a special class of value functions which we call adversarial value functions (AVFs). We demonstrate that using value functions as auxiliary tasks corresponds to an expected-error relaxation of our formulation, with AVFs a natural candidate, and identify a close relationship with proto-value functions (Mahadevan, 2005). We highlight characteristics of AVFs and their usefulness as auxiliary tasks in a series of experiments on the four-room domain.

NeurIPS Conference 2019 Conference Paper

Reducing the variance in online optimization by transporting past gradients

• Sébastien Arnold
• Pierre-Antoine Manzagol
• Reza Babanezhad Harikandeh
• Ioannis Mitliagkas
• Nicolas Le Roux

Most stochastic optimization methods use gradients once before discarding them. While variance reduction methods have shown that reusing past gradients can be beneficial when there is a finite number of datapoints, they do not easily extend to the online setting. One issue is the staleness due to using past gradients. We propose to correct this staleness using the idea of {\em implicit gradient transport} (IGT) which transforms gradients computed at previous iterates into gradients evaluated at the current iterate without using the Hessian explicitly. In addition to reducing the variance and bias of our updates over time, IGT can be used as a drop-in replacement for the gradient estimate in a number of well-understood methods such as heavy ball or Adam. We show experimentally that it achieves state-of-the-art results on a wide range of architectures and benchmarks. Additionally, the IGT gradient estimator yields the optimal asymptotic convergence rate for online stochastic optimization in the restricted setting where the Hessians of all component functions are equal.

ICML Conference 2019 Conference Paper

The Value Function Polytope in Reinforcement Learning

• Robert Dadashi
• Marc G. Bellemare
• Adrien Ali Taïga
• Nicolas Le Roux
• Dale Schuurmans

We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al. , 2010). To demonstrate this result, we exhibit several properties of the structural relationship between policies and value functions including the line theorem, which shows that the value functions of policies constrained on all but one state describe a line segment. Finally, we use this novel perspective and introduce visualizations to enhance the understanding of the dynamics of reinforcement learning algorithms.

ICML Conference 2019 Conference Paper

Understanding the Impact of Entropy on Policy Optimization

• Zafarali Ahmed
• Nicolas Le Roux
• Mohammad Norouzi 0002
• Dale Schuurmans

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with exploration by encouraging the selection of more stochastic policies. In this work, we analyze this claim using new visualizations of the optimization landscape based on randomly perturbing the loss function. We first show that even with access to the exact gradient, policy optimization is difficult due to the geometry of the objective function. We then qualitatively show that in some environments, a policy with higher entropy can make the optimization landscape smoother, thereby connecting local optima and enabling the use of larger learning rates. This paper presents new tools for understanding the optimization landscape, shows that policy entropy serves as a regularizer, and highlights the challenge of designing general-purpose policy optimization algorithms.

ICML Conference 2010 Conference Paper

A fast natural Newton method

• Nicolas Le Roux
• Andrew W. Fitzgibbon