Gaëtan Narozniak

Charles Arnal, Gaëtan Narozniak, Vivien Cabannes et al.

Reinforcement learning (RL) is increasingly used to align large language models (LLMs). Off-policy methods offer greater implementation simplicity and data efficiency than on-policy techniques, but often result in suboptimal performance. In this work, we study the intermediate range of algorithms between off-policy RL and supervised fine-tuning by analyzing a simple off-policy REINFORCE algorithm, where the advantage is defined as $A=r-V$, with $r$ a reward and $V$ some tunable baseline. Intuitively, lowering $V$ emphasizes high-reward samples, while raising it penalizes low-reward ones more heavily. We first provide a theoretical analysis of this off-policy REINFORCE algorithm, showing that when the baseline $V$ lower-bounds the expected reward, the algorithm enjoys a policy improvement guarantee. Our analysis reveals that while on-policy updates can safely leverage both positive and negative signals, off-policy updates benefit from focusing more on positive rewards than on negative ones. We validate our findings experimentally in a controlled stochastic bandit setting and through fine-tuning state-of-the-art LLMs on reasoning tasks.

Gaetan Narozniak, Gérard Biau, Rémi Munos et al.

Post-training for reasoning models typically combines supervised fine-tuning with reinforcement learning from verifiable rewards, most commonly with GRPO. However, this algorithm suffers from sparse rewards, limited exploration, and mode collapse. Building upon recent works on self-distillation, we propose Feedback Distillation, a training method where the model is trained to match, at the token level, its own distribution conditioned on privileged feedback produced by a language model. Feedback Distillation offers token-level supervision and can inject external knowledge. Evaluating our method for Lean4 theorem-proving, we find that Feedback Distillation maintains greater diversity in generated trajectories than GRPO, yielding higher policy entropy and better pass@k scaling. The two methods are complementary: initializing GRPO from a Feedback Distillation checkpoint outperforms either method alone. All in all, our results suggest a promising avenue to improve post-training for complex reasoning.