We study value-iteration (VI) algorithms for solving general (a.k.a.

The fine-tuning of pre-trained large language models (LLMs) using reinforcement learning (RL) is generally formulated as direct policy optimization. This approach was naturally favored as it efficiently improves a pretrained LLM, seen as an initial policy. Another RL paradigm, Q-learning methods, has received far less attention in the LLM community while demonstrating major success in various non-LLMRL tasks. In particular, Q-learning effectiveness comes from its sample efficiency and ability to learn offline, which is particularly valuable given the high computational cost of sampling with LLM. However, naively applying a Q-learning-style update to the model's logits is ineffective due to the specificity of LLMs. Our core contribution is to derive theoretically grounded loss functions from Bellman equations to adapt Q-learning methods to LLMs. To do so, we carefully adapt insights from the RL literature to account for LLM-specific characteristics, ensuring that the logits become reliable Q-value estimates. We then use this loss to build a practical algorithm, ShiQfor Shifted-Q, that supports off-policy, token-wise learning while remaining simple to implement. Finally, we evaluate ShiQ on both synthetic data and real-world benchmarks, e.g., UltraFeedback, BFCL-V3, demonstrating its effectiveness in both single-turn and multi-turn LLM settings.

Expert demonstrations, such as those from car drivers, help navigate environments with unknown rewards, but are often collected in controlled settings, such as closed-course test tracks, while learned control policies must be deployed in new environments, such as city streets. We can imitate experts to perform well in the same source environment where demonstrations are observed, and we may even use inverse reinforcement learning (IRL) to improve on simple behavior cloning (Ng and Russell, 2000; Abbeel and Ng, 2004; Ziebart et al., 2008; Fu et al., 2018; Geng et al., 2020). But the target environment may have a different transition law, discount factor, or soft-control regularization. For this, IRL is crucial: we can learn a reward from demonstrations in the source environment and transfer it to the target environment, learning a policy that optimizes the same reward function in a new setting (Fu et al., 2018; Schlaginhaufen and Kamgarpour, 2024). In this paper, we characterize how well this transfer can be done and which approaches are preferable. In particular, we show the value in a coupled approach that takes the target environment into account even when learning from the source. In ordinary offline control, the Bellman equation uses a known reward, so the main statistical error comes from target transitions.

We propose a new algorithm for model-based distributional reinforcement learning (RL), and prove that it is minimax-optimal for approximating return distributions in the generative model regime (up to logarithmic factors), the first result of this kind for any distributional RL algorithm. Our analysis also provides new theoretical perspectives on categorical approaches to distributional RL, as well as introducing a new distributional Bellman equation, the stochastic categorical CDF Bellman equation, which we expect to be of independent interest. Finally, we provide an experimental study comparing a variety of model-based distributional RL algorithms, with several key takeaways for practitioners.

We conduct a novel theoretical analysis to demonstrate CODA's

This paper is about the problem of learning a stochastic policy for generating an object (like a molecular graph) from a sequence of actions, such that the probability of generating an object isproportional to agiven positivereward for that object.