论文检索

Reinforcement Learning · Batch/Offline

Zhiwei XU, Miduo Cui, Dapeng Li, Zhihao Liu, Haifeng Zhang, Hangyu Mao, Guoliang Fan, Bin Zhang

Offline reinforcement learning enables policy learning solely from fixed datasets, without costly or risky environment interactions, making it highly valuable for real-world applications. While Transformer-based approaches have recently demonstrated strong sequence modeling capabilities, they typically learn from complete trajectories conditioned on final returns. To mitigate this limitation, we propose the Peak-Return Greedy Slicing (PRGS) framework, which explicitly partitions trajectories at the timestep level and emphasizes high-quality subtrajectories. PRGS first leverages an MMD-based return estimator to characterize the distribution of future returns for state-action pairs, yielding optimistic return estimates. It then performs greedy slicing to extract high-quality subtrajectories for training. During evaluation, an adaptive history truncation mechanism is introduced to align the inference process with the training procedure. Extensive experiments across multiple benchmark datasets indicate that PRGS significantly improves the performance of Transformer-based offline reinforcement learning methods by effectively enhancing their ability to exploit and recombine valuable subtrajectories.

Reinforcement Learning · Batch/Offline

Shengchao Hu, Peng Wang, Guozheng Ma, Shi Fu, Li Shen, Ya Zhang, Dacheng Tao

Reinforcement finetuning (RFT) has garnered significant attention in recent years, particularly for enhancing large reasoning models such as OpenAI o1 and Deepseek R1. The appeal of RFT largely stems from its ability to refine model knowledge, better align outputs with user intent, and address challenges associated with limited finetuning data. Despite these advantages, the application of RFT in large Transformer-based generative agents remains relatively underexplored. Although these agents are designed to address multiple tasks through large-scale autoregressive pretraining and share many properties with large reasoning models, current adaptation strategies predominantly rely on supervised finetuning (SFT). In this work, we conduct a systematic investigation of several RFT techniques across a variety of finetuning parameter configurations and meta-reinforcement learning (meta-RL) environments, employing few-shot offline datasets. We provide a comprehensive analysis of RFT algorithm performance under diverse experimental conditions and, based on our empirical findings, introduce a lightweight enhancement to existing RFT methods. This enhancement consistently improves outcomes by combining the strengths of both SFT and RFT. Our findings provide valuable insights for advancing the effectiveness of RFT approaches and broadening their applicability to meta-RL tasks with large Transformer-based generative agents, motivating further research in broader domains.

Reinforcement Learning · Batch/Offline

Wenhong Zhu, Ruobing Xie, Rui Wang, Samm Sun, Di Wang, Pengfei Liu

Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on specific tasks. Inspired by trust-region policy optimization (TRPO) and proximal policy optimization (PPO) in reinforcement learning (RL), we propose Proximal SFT (PSFT), a fine-tuning objective that incorporates the benefits of trust-region, effectively constraining policy drift during SFT while maintaining competitive tuning. By viewing SFT as a special case of policy gradient methods with constant positive advantages, we derive PSFT that stabilizes optimization and leads to generalization, while leaving room for further optimization in subsequent post-training stages. Experiments across mathematical, human-value, and multimodal domains show that PSFT matches standard SFT in-domain, outperforms it in out-of-domain generalization, remains stable under prolonged training without causing entropy collapse, and provides a stronger foundation for the subsequent optimization.

Reinforcement Learning · Batch/Offline

Huazhong Wang, Wenzhuo Zhou

We study reinforcement learning (RL) with trajectory preferences, where the RL agent does not receive explicit rewards at each step but instead receives human-AI preferences over pairs of trajectories. Despite growing interest in preference-based reinforcement learning (PbRL), contemporary works cannot robustly learn policies in offline settings with poor data coverage and often lack algorithmic tractability. We propose a novel **M**odel-based **C**onservative **P**lanning (MCP) algorithm for offline PbRL, which leverages a general function class and uses a tractable conservative learning framework to improve the policy upon an arbitrary reference policy. We prove that, MCP can compete with the best policy within data coverage when the reference policy is supported by the data. To the best of our knowledge, MCP is the first provably sample-efficient and computationally tractable offline PbRL algorithm under partial data coverage, without requiring known transition dynamics. We further demonstrate that, with certain structural properties in PbRL dynamics, our algorithm can effectively exploit these structures to relax the partial data coverage requirement and improve regret guarantees. We evaluate MCP on a comprehensive suite of human-in-the-loop benchmarks in Meta-World. Experimental results show that our algorithm achieves competitive performance compared to state-of-the-art offline PbRL algorithms. Our code is provided at https://github.com/Rshias/MCP.

Reinforcement Learning · Batch/Offline

Songyuan Zhang, Oswin So, H M Sabbir Ahmad, Eric Yu, Matthew Cleaveland, Mitchell Black, Chuchu Fan

Offline reinforcement learning (RL) aims to learn the optimal policy from a fixed dataset generated by behavior policies without additional environment interactions. One common challenge that arises in this setting is the out-of-distribution (OOD) error, which occurs when the policy leaves the training distribution. Prior methods penalize a statistical distance term to keep the policy close to the behavior policy, but this constrains policy improvement and may not completely prevent OOD actions. Another challenge is that the optimal policy distribution can be multimodal and difficult to represent. Recent works apply diffusion or flow policies to address this problem, but it is unclear how to avoid OOD errors while retaining policy expressiveness. We propose ReFORM, an offline RL method based on flow policies that enforces the less restrictive support constraint by construction. ReFORM learns a behavior cloning (BC) flow policy with a bounded source distribution to capture the support of the action distribution, then optimizes a reflected flow that generates bounded noise for the BC flow while keeping the support, to maximize the performance. Across 40 challenging tasks from the OGBench benchmark with datasets of varying quality and using a constant set of hyperparameters for all tasks, ReFORM dominates all baselines with hand-tuned hyperparameters on the performance profile curves.

Reinforcement Learning · Batch/Offline

Qiyang Li, Sergey Levine

We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm that tackles a long-standing challenge in continuous-action RL: efficient optimization of an expressive diffusion or flow-matching policy with respect to a parameterized Q-function. Effective optimization requires exploiting the first-order information of the critic, but it is challenging to do so for flow or diffusion policies because direct gradient-based optimization via backpropagation through their multi-step denoising process is numerically unstable. Existing methods work around this either by only using the value and discarding the gradient information, or by relying on approximations that sacrifice policy expressivity or bias the learned policy. QAM sidesteps both of these challenges by leveraging adjoint matching, a recently proposed technique in generative modeling, which transforms the critic's action gradient to form a step-wise objective function that is free from unstable backpropagation, while providing an unbiased, expressive policy at the optimum. Combined with temporal-difference backup for critic learning, QAM consistently outperforms prior approaches on hard, sparse reward tasks in both offline and offline-to-online RL.

Reinforcement Learning · Batch/Offline

Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin, Artyom Grishin, Igor Saprygin, Aleksandr Serkov, Mark Averchenko, Daniil Tikhonov, Maksim Zhdanov, Alexander Nikulin 等

Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorithm Distillation (AD) pioneered this paradigm and was subsequently scaled to multi-domain settings, although its ability to generalize to unseen tasks remained limited. The Decision Pre-Trained Transformer (DPT) was introduced as an alternative, showing stronger in-context reinforcement learning abilities in simplified domains, but its scalability had not been established. In this work, we extend DPT to diverse multi-domain environments, applying Flow Matching as a natural training choice that preserves its interpretation as Bayesian posterior sampling. As a result, we obtain an agent trained across hundreds of diverse tasks that achieves clear gains in generalization to the held-out test set. This agent improves upon prior AD scaling and demonstrates stronger performance in both online and offline inference, reinforcing ICRL as a viable alternative to expert distillation for training generalist agents.

Reinforcement Learning · Batch/Offline

Hyungkyu Kang, Min-hwan Oh

We study the problem of offline preference-based reinforcement learning (PbRL), where the agent learns from pre-collected preference data by comparing trajectory pairs. While prior work has established theoretical foundations for offline PbRL, existing algorithms face significant practical limitations: some rely on computationally intractable optimization procedures, while others suffer from unstable training and high performance variance. To address these challenges, we propose Preference-based Value Optimization (PVO), a simple and practical algorithm that achieves both strong empirical performance and theoretical guarantees. PVO directly optimizes the value function consistent with preference feedback by minimizing a novel \emph{value alignment loss}. We prove that PVO attains a rate-optimal sample complexity of $\mathcal{O}(\varepsilon^{-2})$, and further show that the value alignment loss is applicable not only to value-based methods but also to actor–critic algorithms. Empirically, PVO achieves robust and stable performance across diverse continuous control benchmarks. It consistently outperforms strong baselines, including methods without theoretical guarantees, while requiring no additional hyperparameters for preference learning. Moreover, our ablation study demonstrates that substituting the standard TD loss with the value alignment loss substantially improves learning from preference data, confirming its effectiveness for PbRL.

Reinforcement Learning · Batch/Offline

Byeongchan Kim, Min-hwan Oh

We propose a model-free offline multi-step reinforcement learning (RL) algorithm, Conservative Peng's Q($\lambda$) (CPQL). Our algorithm adapts the Peng's Q($\lambda$) (PQL) operator for conservative value estimation as an alternative to the Bellman operator. To the best of our knowledge, this is the first work in offline RL to theoretically and empirically demonstrate the effectiveness of conservative value estimation with the \textit{multi-step} operator by fully leveraging offline trajectories. The fixed point of the PQL operator in offline RL lies closer to the value function of the behavior policy, thereby naturally inducing implicit behavior regularization. CPQL simultaneously mitigates over-pessimistic value estimation, achieves performance greater than (or equal to) that of the behavior policy, and provides near-optimal performance guarantees --- a milestone that previous conservative approaches could not achieve. Extensive numerical experiments on the D4RL benchmark demonstrate that CPQL consistently and significantly outperforms existing offline single-step baselines. In addition to the contributions of CPQL in offline RL, our proposed method also contributes to the offline-to-online learning framework. Using the Q-function pre-trained by CPQL in offline settings enables the online PQL agent to avoid the performance drop typically observed at the start of fine-tuning and to attain robust performance improvements. Our code is available at https://github.com/oh-lab/CPQL.

Reinforcement Learning · Batch/Offline

Franki NGUIMATSIA TIOFACK, Théotime Le Hellard, Fabian Schramm, Nicolas Perrin-Gilbert, Justin Carpentier

Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their regularization components. We introduce Guided Flow Policy (GFP), which couples a multi-step flow-matching policy with a distilled one-step actor. The actor directs the flow policy through weighted behavior cloning to focus on cloning high-value actions from the dataset rather than indiscriminately imitating all state-action pairs. In turn, the flow policy constrains the actor to remain aligned with the dataset's best transitions while maximizing the critic. This mutual guidance enables GFP to achieve state-of-the-art performance across 144 state and pixel-based tasks from the OGBench, Minari, and D4RL benchmarks, with substantial gains on suboptimal datasets and challenging tasks.

Reinforcement Learning · Batch/Offline

Qiushui Xu, Yuhao Huang, Yushu Jiang, Wenliang Zheng, Lei Song, Jinyu Wang, Jiang Bian

Accurate estimation of the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a shared global Q-function, which is inadequate for capturing the compositional structure of tasks that consist of diverse subtasks. We propose In-context Compositional Q-Learning (ICQL), an offline RL framework that formulates Q-learning as a contextual inference problem and uses linear Transformers to adaptively infer local Q-functions from retrieved transitions without explicit subtask labels. Theoretically, we show that, under two assumptions---linear approximability of the local Q-function and accurate inference of weights from retrieved context---ICQL achieves a bounded approximation error for the Q-function and enables near-optimal policy extraction. Empirically, ICQL substantially improves performance in offline settings, achieving gains of up to 16.4\% on kitchen tasks and up to 8.8\% and 6.3\% on MuJoCo and Adroit tasks, respectively. These results highlight the underexplored potential of in-context learning for robust and compositional value estimation and establish ICQL as a principled and effective framework for offline RL.

Reinforcement Learning · Batch/Offline

Yuxuan Tang, Yifan Feng

Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from richer forms of human feedback, such as multiway comparisons and top-$k$ rankings. We introduce \textit{Ranked Choice Preference Optimization} (RCPO), a unified framework that bridges preference optimization with (ranked) choice modeling via maximum likelihood estimation. RCPO supports both utility-based and rank-based models, subsumes several pairwise methods (such as DPO and SimPO) as special cases, and provides principled training objectives for richer feedback formats. We instantiate this framework with two representative models (Multinomial Logit and Mallows-RMJ). Experiments on Llama-3-8B-Instruct, Gemma-2-9B-it, and Mistral-7B-Instruct across in-distribution and out-of-distribution settings show that RCPO consistently outperforms competitive baselines. RCPO shows that directly leveraging ranked preference data, combined with the right choice models, yields more effective alignment. It offers an extensible foundation for incorporating (ranked) choice modeling into LLM training.

Reinforcement Learning · Batch/Offline

Jiahui Zhu, Yuanjie Shi, Xiyue Peng, Xin Liu, Yan Yan, Honghao Wei

Direct Preference Optimization (DPO) has emerged as a powerful framework for aligning large language models (LLMs) with human preferences via pairwise comparisons. However, its performance is highly sensitive to the quality of training samples: when the reference policy is poorly aligned with human preferences, ambiguous pairs can dominate the gradient signal and degrade generalization. To address this, we propose RAPPO($\textbf{R}$eliable $\textbf{A}$lignment for $\textbf{P}$reference $\textbf{P}$olicy $\textbf{O}$ptimization), a simple sample-aware modification of the DPO loss that mitigates reference-policy misalignment by filtering out the hardest, most ambiguous samples. We theoretically show that RAPPO yields improved generalization guarantees. RAPPO is lightweight and requires only a few lines of code to be integrated into any existing DPO-type algorithm. Surprisingly, With this simple modification, our simulations across a broad suite of alignment tasks and benchmarks show consistent gains over DPO and recent state-of-the-art baselines. On the PKU-SafeRLHF benchmark, RAPPO attains helpfulness $0.693$ ($+34.8\%$ over DPO) and harmlessness $0.357$ ($-21.0\%$ vs DPO).

Reinforcement Learning · Batch/Offline

Zeyu Feng, Haiyan Yin, Yew-Soon Ong, Harold Soh

Generalizing policies across environments with altered dynamics remains a key challenge in reinforcement learning, particularly in offline settings where direct interaction or fine-tuning is impractical. We introduce Masked Skill Token Training (MSTT), a fully offline hierarchical RL framework that enables policy transfer using observation-only demonstrations. MSTT constructs a discrete skill space via unsupervised trajectory tokenization and trains a skill-conditioned value function using masked Bellman updates, which simulate dynamics shifts by selectively disabling skills. A diffusion-based trajectory generator, paired with feasibility-based filtering, enables the agent to execute valid, temporally extended actions without requiring action labels or access to the target environment. Our results in both discrete and continuous domains demonstrate the potential of mask-guided planning for robust generalization under dynamics shifts. To our knowledge, MSTT is the first work to explore masking as a mechanism for simulating and generalizing across off-dynamics environments. It marks a promising step toward scalable, structure-aware transfer and opens avenues to explore multi-goal conditioning, and extensions to more complex, real-world scenarios.

Reinforcement Learning · Batch/Offline

Haruki Abe, Takayuki Osa, YUSUKE Mukuta, Tatsuya Harada

Scalable robot policy pre-training has been hindered by the high cost of collecting high-quality demonstrations for each platform. In this study, we address this issue by uniting offline reinforcement learning (offline RL) with cross-embodiment learning. Offline RL leverages both expert and abundant suboptimal data, and cross-embodiment learning aggregates heterogeneous robot trajectories across diverse morphologies to acquire universal control priors. We perform a systematic analysis of this offline RL and cross-embodiment paradigm, providing a principled understanding of its strengths and limitations. To evaluate this offline RL and cross-embodiment paradigm, we construct a suite of locomotion datasets spanning 16 distinct robot platforms. Our experiments confirm that this combined approach excels at pre-training with datasets rich in suboptimal trajectories, outperforming pure behavior cloning. However, as the proportion of suboptimal data and the number of robot types increase, we observe that conflicting gradients across morphologies begin to impede learning. To mitigate this, we introduce an embodiment-based grouping strategy in which robots are clustered by morphological similarity and the model is updated with a group gradient. This simple, static grouping substantially reduces inter-robot conflicts and outperforms existing conflict-resolution methods. Project page: https://haruki-abe.github.io/cross_embodiment_offline_rl_website

Reinforcement Learning · Batch/Offline

Jongseong Chae, Jongeui Park, Yongjae Shin, Gyeongmin Kim, Seungyul Han, Youngchul Sung

The dataset distributions in offline reinforcement learning (RL) often exhibit complex and multi-modal distributions, necessitating expressive policies to capture such distributions beyond widely-used Gaussian policies. To handle such complex and multi-modal datasets, in this paper, we propose Flow Actor-Critic, a new actor-critic method for offline RL, based on recent flow policies. The proposed method not only uses the flow model for actor as in previous flow policies but also exploits the expressive flow model for conservative critic acquisition to prevent Q-value explosion in out-of-data regions. To this end, we propose a new form of critic regularizer based on the flow behavior proxy model obtained as a byproduct of flow-based actor design. Leveraging the flow model in this joint way, we achieve new state-of-the-art performance for test datasets of offline RL including the D4RL and recent OGBench benchmarks.

Reinforcement Learning · Batch/Offline

Natinael Neggatu, Jeremie Houssineau, Giovanni Montana

Most existing offline RL methods presume the availability of action labels within the dataset, but in many practical scenarios, actions may be missing due to privacy, storage, or sensor limitations. We formalise the setting of action-free offline-to-online RL, where agents must learn from datasets consisting solely of $(s,r,s')$ tuples and later leverage this knowledge during online interaction. To address this challenge, we propose learning state policies that recommend desirable next-state transitions rather than actions. Our contributions are twofold. First, we introduce a simple yet novel state discretisation transformation and propose Offline State-Only DecQN (OSO-DecQN), a value-based algorithm designed to pre-train state policies from action-free data. OSO-DecQN integrates the transformation to scale efficiently to high-dimensional problems while avoiding instability and overfitting associated with continuous state prediction. Second, we propose a novel mechanism for guided online learning that leverages these pre-trained state policies to accelerate the learning of online agents. Together, these components establish a scalable and practical framework for leveraging action-free datasets to accelerate online RL. Empirical results across diverse benchmarks demonstrate that our approach improves convergence speed and asymptotic performance, while analyses reveal that discretisation and regularisation are critical to its effectiveness.

Reinforcement Learning · Batch/Offline

Zhuohao Yu, Steven Wu, Adam Block

Inference-time compute scaling has emerged as a powerful paradigm for improving language model performance on a wide range of tasks, but the question of how best to use the additional compute remains open. A popular approach is *Best-of-$N$* (BoN) sampling, where $N$ candidate responses are generated, scored according to a reward model, and the highest-scoring response is selected. While this approach can improve performance, it is vulnerable to *reward hacking*, where performance degrades as $N$ increases due to the selection of responses that exploit imperfections in the reward model instead of genuinely improving generation quality. Prior attempts to mitigate reward hacking---via stronger reward models or heavy-handed distributional regularization---either fail to fully address over-optimization or are too conservative to exploit additional compute. In this work, we explore the principle of *pessimism* in reinforcement learning (RL), which uses lower confidence bounds on value estimates to avoid out-of-distribution (OOD) actions with uncertain reward estimates. Our approach, termed as *caution*, can be seen as the *reverse* of *curiosity*: where curiosity (e.g., via Random Network Distillation, RND) rewards prediction error as a signal of novelty, caution penalizes prediction error as a signal of distributional uncertainty. Practically, caution trains an error model on typical responses and uses its prediction error to lower reward estimates for atypical ones. Our extensive empirical evaluation demonstrates that caution is a simple, computationally efficient approach that substantially mitigates reward hacking in BoN sampling. We also provide a theoretical analysis in a simplified linear setting, which shows that caution provably improves over the standard BoN approach. Together, our results not only establish caution as a practical solution to reward hacking, but also provide evidence that curiosity-based approaches can be a general OOD detection technique in LLM settings.

Reinforcement Learning · Batch/Offline

Pragya Srivastava, Harman Singh, Rahul Madhavan, Gandharv Patil, Sravanti Addepalli, Arun Suggala, Rengarajan Aravamudhan, Soumya Sharma, Anirban Laha, Aravindan Raghuveer 等

Reward models (RMs) are fundamental to aligning Large Language Models (LLMs) via human feedback, yet they often suffer from reward hacking. They tend to latch on to superficial or spurious attributes, such as response length or formatting, mistaking these cues learned from correlations in training data for the true causal drivers of quality (e.g., factuality, relevance). This occurs because standard training objectives struggle to disentangle these factors, leading to brittle RMs and misaligned policies. We introduce CROME (Causally Robust Reward Modeling), a novel framework inspired by an explicit causal model designed to mitigate reward hacking. CROME queries an oracle LLM for rubrics that are (or the oracle deems to be) causally relevant to answering a specific prompt. Then, it employs the following synthetic targeted augmentations during training: (1) Causal Augmentations, which are pairs that differ along specific causal attributes (subset of the Oracle identified rubrics), to enforce sensitivity along each causal attribute individually, and (2) Neutral Augmentations, which are tie-label pairs varying primarily in spurious attributes, to enforce invariance along spurious attributes. Notably, our neutral augmentations are produced without any knowledge of unknown spurious factors, via question swapping and response interventions only along causal rubrics. We show that the CROME augmentation strategy using rubrics from popular LLM APIs significantly outperforms standard baselines on RewardBench, improving average accuracy by up to 5.3% and achieving gains of up to 7.1% and 12.4% in reasoning and safety. The robustness of CROME is further testified by significant gains in DPO-aligned policies and Best-of-N alignment across various benchmarks, including AlpacaEval 2.0, RewardBench, safety-focused WildGuardTest, and the reasoning-specific GSM8k.

Reinforcement Learning · Batch/Offline

Jinmei Liu, Fuhong Liu, Zhenhong Sun, Jianye Hao, Huaxiong Li, Bo Wang, Daoyi Dong, Chunlin Chen, Zhi Wang

Recent advancements in language models have demonstrated remarkable in-context learning abilities, prompting the exploration of in-context reinforcement learning (ICRL) to extend the promise to decision domains. Due to involving more complex dynamics and temporal correlations, existing ICRL approaches may face challenges in learning from suboptimal trajectories and achieving precise in-context inference. In the paper, we propose **S**calable **I**n-**C**ontext **Q**-**L**earning (**S-ICQL**), an innovative framework that harnesses dynamic programming and world modeling to steer ICRL toward efficient reward maximization and task generalization, while retaining the scalability and stability of supervised pretraining. We design a prompt-based multi-head transformer architecture that simultaneously predicts optimal policies and in-context value functions using separate heads. We pretrain a generalized world model to capture task-relevant information, enabling the construction of a compact prompt that facilitates fast and precise in-context inference. During training, we perform iterative policy improvement by fitting a state value function to an upper-expectile of the Q-function, and distill the in-context value functions into policy extraction using advantage-weighted regression. Extensive experiments across a range of discrete and continuous environments show consistent performance gains over various types of baselines, especially when learning from suboptimal data. Our code is available at [https://github.com/NJU-RL/SICQL](https://github.com/NJU-RL/SICQL).