Healthcare Policy Modeling

Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We trace this instability to a fundamental connection: the flow rollout is algebraically equivalent to a residual recurrent computation, making it susceptible to the same vanishing and exploding gradients as RNNs. To address this, we reparameterize the velocity network using principles from modern sequential models, introducing two stable architectures: Flow-G, which incorporates a gated velocity, and Flow-T, which utilizes a decoded velocity. We then develop a practical SAC-based algorithm, enabled by a noise-augmented rollout, that facilitates direct end-to-end training of these policies. Our approach supports both from-scratch and offline-to-online learning and achieves state-of-the-art performance on continuous control and robotic manipulation benchmarks, eliminating the need for common workarounds like policy distillation or surrogate objectives. Anonymized code is available at \url{https://anonymous.4open.science/r/SAC-FLOW}

Self-supervised feature learning and pretraining methods in reinforcement learning (RL) often rely on information-theoretic principles, termed mutual information skill learning (MISL). These methods aim to learn a representation of the environment while also incentivizing exploration thereof. However, the role of the representation and mutual information parametrization in MISL is not yet well understood theoretically. Our work investigates MISL through the lens of identifiable representation learning by focusing on the Contrastive Successor Features (CSF) method. We prove that CSF can provably recover the environment's ground-truth features up to a linear transformation due to the inner product parametrization of the features and skill diversity in a discriminative sense. This first identifiability guarantee for representation learning in RL also helps explain the implications of different mutual information objectives and the downsides of entropy regularizers. We empirically validate our claims in MuJoCo and DeepMind Control and show how CSF provably recovers the ground-truth features both from states and pixels.

Discrete latent bottlenecks in variational autoencoders (VAEs) offer high bit efficiency and can be modeled with autoregressive discrete distributions, enabling parameter-efficient multimodal search with transformers. However, discrete random variables do not allow for exact differentiable parameterization; therefore, discrete VAEs typically rely on approximations, such as Gumbel-Softmax reparameterization or straight-through gradient estimates, or employ high-variance gradient-free methods such as REINFORCE that have had limited success on high-dimensional tasks such as image reconstruction. Inspired by popular techniques in policy search, we propose a training framework for discrete VAEs that leverages the natural gradient of a non-parametric encoder to update the parametric encoder without requiring reparameterization. Our method, combined with automatic step size adaptation and a transformer-based encoder, scales to challenging datasets such as ImageNet and outperforms both approximate reparameterization methods and quantization-based discrete autoencoders in reconstructing high-dimensional data from compact latent spaces.

Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely heavily on expert demonstrations, which not only lack explicit safety awareness but also risk inheriting undesirable behaviors such as speeding from suboptimal human driving data. Inspired by the success of large language models, we propose Plan-R1, a two-stage trajectory planning framework that decouples principle alignment from behavior learning. In the first stage, a general trajectory predictor is pre-trained on expert data to capture diverse, human-like driving behaviors. In the second stage, the model is fine-tuned with rule-based rewards using Group Relative Policy Optimization (GRPO), explicitly aligning ego planning with principles such as safety, comfort, and traffic rule compliance. This two-stage paradigm retains human-like behaviors while enhancing safety awareness and discarding undesirable patterns from demonstrations. Furthermore, we identify a key limitation of directly applying GRPO to planning: group-wise normalization erases cross-group scale differences, causing rare, high-variance safety-violation groups to have similar advantages as abundant low-variance safe groups, thereby suppressing optimization for safety-critical objectives. To address this, we propose Variance-Decoupled GRPO (VD-GRPO), which replaces normalization with centering and fixed scaling to preserve absolute reward magnitudes, ensuring that safety-critical objectives remain dominant throughout training. Experiments on the nuPlan benchmark demonstrate that Plan-R1 significantly improves planning safety and feasibility, achieving state-of-the-art performance, particularly in realistic reactive settings.

In reinforcement learning (RL), critics traditionally learn absolute state values, estimating how good a particular situation is in isolation. Adding any constant to $V(s)$ leaves action preferences unchanged. Thus only value differences are relevant for decision making. Motivated by this fact, we ask the question whether these differences can be learned directly. For this, we propose \emph{Relative Value Learning} (RV), a framework that considers antisymmetric value differences $\Delta(s_i, s_j) = V(s_i) - V(s_j)$. We define a new pairwise Bellman operator and prove it is a $\gamma$-contraction with a unique fixed point equal to the true value differences, derive well-posed $1$-step/$n$-step/$\lambda$-return targets and reconstruct generalized advantage estimation from pairwise differences to obtain an unbiased policy-gradient estimator (R-GAE). Besides rigorous theoretical contributions, we integrate RV with PPO and achieve competitive performance on the Atari benchmark (49 games, ALE) compared to standard PPO, indicating that relative value estimation is an effective alternative to absolute critics. Source code will be made available.

The alignment of language models (LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences. Recently, Direct Preference Optimization (DPO) was proposed as a LM alignment method that directly optimize the policy from static preference data, and further improved by incorporating on-policy sampling (i.e., preference candidates generated during the training loop) for better LM alignment. However, we show on-policy data is not always optimal, with systematic effectiveness difference emerging between static and on-policy preference candidates. For example, on-policy data can result in a $3\times$ effectiveness compared with static data for Llama-3, and a $0.4\times$ effectiveness for Zephyr. To explain the phenomenon, we propose the alignment stage assumption, which divides the alignment process into two distinct stages: the preference injection stage, which benefits from diverse data, and the preference fine-tuning stage, which favors high-quality data. Through theoretical and empirical analysis, we characterize these stages and propose an effective algorithm to identify the boundaries between them. We perform experiments on $5$ models (Llama, Zephyr, Phi-2, Qwen, Pythia) and $2$ alignment methods (DPO, SLiC-HF) to show the generalizability of alignment stage assumption and boundary measurement.

Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs), yet most existing Reinforcement Finetuning (RFT) methods are inherently \textit{on-policy} RL, failing to reuse historical data and thus preventing efficient scaling. In this work, we explore the potential of \textit{off-policy} RL to leverage historical data for rollout-efficient RFT. Specifically, we propose \textbf{Re}incarnating \textbf{Mix}-policy Proximal Policy Gradient (\textbf{ReMix}), which enables on-policy RFT methods to leverage off-policy data. ReMix consists of three major components: (1) Mix-policy proximal policy gradient with an increased Update-To-Data (UTD) ratio that utilizes the data from both current and past policies for efficient training; (2) KL-Convex policy constraint that combines the KL constraints on the base and precedent model to balance stability and flexibility; (3) Policy reincarnation that replaces the base model with the mix-policy RFT model in the mid way of training and restarts on-policy training, to achieve a seamless transition from early efficiency to steady convergence. In our experiments, we train a series of ReMix models based on PPO, GRPO from 1.5B, 7B base models. On five math reasoning benchmarks (i.e., AIME'24, AMC'23, Minerva, OlympiadBench, and MATH500), ReMix achieves an average Pass@1 accuracy of \textbf{52.10\%} (with \textbf{0.079M rollouts}) and \textbf{64.39\%} (with \textbf{0.011M rollouts}) on 1.5B and 7B models, respectively. Compared with 15 recent advanced models, ReMix shows SOTA-level performance with an over \textbf{30x to 450x reduction in training cost in terms of rollout data volume}, demonstrating superior training efficiency. Additionally, our multifaceted analysis reveals insightful findings, including the implicit preference for shorter responses of off-policy RFT, the collapse mode of self-reflection under severe off-policyness, etc.

In this paper, we explore how directly pretraining a value model simplifies and stabilizes reinforcement learning from human feedback (RLHF). In reinforcement learning, value estimation is the key to policy optimization, distinct from reward supervision. The value function predicts the \emph{return-to-go} of a partial answer, that is, how promising the partial answer is if it were continued to completion. In RLHF, however, the standard pipeline first pretrains a reward model and then learns a value function online, even though no new reward signals are available once preference data is collected. This makes critic learning redundant, as the process of training a reward model and then deriving a value model is informationally equivalent to directly pretraining a value model. Importantly, this requires no additional supervision, and our value model is trained on exactly the same data used for reward modeling. Building on this insight, we introduce \emph{Decoupled Value Policy Optimization} (DVPO), a framework that pretrains a \emph{Global Value Model} (GVM) offline and freezes it as a universal critic for policy learning. The GVM provides stable, fine-grained credit assignment without critic drift or trajectory sampling. Experiments across MT-Bench, Alpaca-Eval, and Arena-Hard demonstrate that DVPO matches or surpasses state-of-the-art RLHF methods. These results highlight RLHF can be reframed as policy-only optimization guided by a single pretrained value model. The implementation code for our method is available in \url{https://github.com/microsoft/DKI_LLM/tree/main/dvpo}

Humans often juggle multiple, sometimes conflicting objectives and shift their priorities as circumstances change, rather than following a fixed objective function. In contrast, most computational decision-making and multi-objective RL methods assume static preference weights or a known scalar reward. In this work, we study sequential decision-making problem when these preference weights are unobserved latent variables that drift with context. Specifically, we propose Dynamic Preference Inference (DPI), a cognitively inspired framework in which an agent maintains a probabilistic belief over preference weights, updates this belief from recent interaction, and conditions its policy on inferred preferences. We instantiate DPI as a variational preference inference module trained jointly with a preference-conditioned actor–critic, using vector-valued returns as evidence about latent trade-offs. In queueing, gridworld maze, and multi-objective continuous-control environments with event-driven changes in objectives, DPI adapts its inferred preferences to new regimes and achieves higher post-shift performance than fixed-weight and heuristic envelope baselines.

Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in reward misspecification at the high-reward tail: the inability to reliably distinguish excellent responses from merely great ones. This motivate us to focus on the high-reward region. However, such tail examples are scarce under the base LLM. While off-policy exemplars (e.g. from stronger models or rewrites) are easier to obtain, naively training on them yields a misspecified reward for the policy we aim to align. To address this, we study rubric-based rewards. By design, rubrics can leverage off-policy examples while remaining insensitive to their artifacts. To elicit rubrics that capture the high-reward tail, we highlight the importance of distinguishing among great and diverse responses, and introduce a workflow to implement this idea. We empirically demonstrate that rubric-based rewards substantially mitigate reward over-optimization and deliver effective LLM post-training improvements.

Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness and computational burden, which is typically controlled by the number of flow steps. In this work, we propose mean flow policy (MFP), a new generative policy function that models the mean velocity field to achieve the fastest one-step action generation. To ensure its high expressiveness, an instantaneous velocity constraint (IVC) is introduced on the mean velocity field during training. We theoretically prove that this design explicitly serves as a crucial boundary condition, thereby improving learning accuracy and enhancing policy expressiveness. Empirically, our MFP achieves state-of-the-art success rates across several challenging robotic manipulation tasks from Robomimic and OGBench. It also delivers substantial improvements in training and inference speed over existing flow-based policy baselines.

While existing multivariate time series forecasting models have advanced significantly in modeling periodicity, they largely neglect the periodic heterogeneity common in real-world data, where variables exhibit distinct and dynamically changing periods. To effectively capture this periodic heterogeneity, we propose PHAT (Period Heterogeneity-Aware Transformer). Specifically, PHAT arranges multivariate inputs into a three-dimensional "periodic bucket" tensor, where the dimensions correspond to variable group characteristics with similar periodicity, time steps aligned by phase, and offsets within the period. By restricting interactions within buckets and masking cross-bucket connections, PHAT effectively avoids interference from inconsistent periods. We also propose a positive-negative attention mechanism, which captures periodic dependencies from two perspectives: periodic alignment and periodic deviation. Additionally, the periodic alignment attention scores are decomposed into positive and negative components, with a modulation term encoding periodic priors. This modulation constrains the attention mechanism to more faithfully reflect the underlying periodic trends. A mathematical explanation is provided to support this property. We evaluate PHAT comprehensively on 14 real-world datasets against 18 baselines, and the results show that it significantly outperforms existing methods, achieving highly competitive forecasting performance. Our sources is available at GitHub.

Generative Flow Networks (GFlowNets) were developed to learn policies for efficiently sampling combinatorial candidates by interpreting their generative processes as trajectories in directed acyclic graphs. In the value-based training workflow, the objective is to enforce the balance over partial episodes between the flows of the learned policy and the estimated flows of the desired policy, implicitly encouraging policy divergence minimization. The policy-based strategy alternates between estimating that divergence and updating the policy, but reliable estimation of the divergence under directed acyclic graphs remains a major challenge. This work bridges the two perspectives by showing that flow balance also yields a principled policy evaluator that measures the policy divergence, and an evaluation balance objective over partial episodes is proposed for learning the evaluator. As demonstrated on both synthetic and real-world tasks, the flow balance condition not only strengthens the reliability of policy-based training but also broadens its flexibility by seamlessly supporting parameterized backward policies and enabling the integration of offline data-collection techniques.

We study computationally and statistically efficient reinforcement learning under the linear $Q^{\pi}$ realizability assumption, where any policy's $Q$-function is linear in a given state-action feature representation. Prior methods in this setting are either computationally intractable, or require (local) access to a simulator. In this paper, we propose a computationally efficient online RL algorithm, named \emph{Frozen Policy Iteration}, under the linear $Q^{\pi}$ realizability setting that works for Markov Decision Processes (MDPs) with stochastic initial states, stochastic rewards and deterministic transitions. Our algorithm achieves a regret bound of $\widetilde{O}(\sqrt{d^2H^6T})$, where $d$ is the dimensionality of the feature space, $H$ is the horizon length, and $T$ is the total number of episodes. Our regret bound is optimal for linear (contextual) bandits which is a special case of our setting with $H = 1$. Existing policy iteration algorithms under the same setting heavily rely on repeatedly sampling the same state by access to the simulator, which is not implementable in the online setting with stochastic initial states studied in this paper. In contrast, our new algorithm circumvents this limitation by strategically using only high-confidence part of the trajectory data and freezing the policy for well-explored states, which ensures that all data used by our algorithm remains effectively \emph{on-policy} during the whole course of learning. We further demonstrate the versatility of our approach by extending it to the Uniform-PAC setting and to function classes with bounded eluder dimension.

The branch-and-bound (B\&B) method is a dominant exact algorithm for solving Mixed-Integer Linear Programming problems (MILPs). While recent deep learning approaches have shown promise in learning branching policies using instance-independent features, they often struggle to capture the sequential decision-making nature of B\&B, particularly over long horizons with complex inter-step dependencies and intra-step variable interactions. To address these challenges, we propose Mamba-Branching, a novel learning-based branching policy that leverages the Mamba architecture for efficient long-sequence modeling, enabling effective capture of temporal dynamics across B\&B steps. Additionally, we introduce a contrastive learning strategy to pre-train discriminative embeddings for candidate branching variables, significantly enhancing Mamba's performance. Experimental results demonstrate that Mamba-Branching outperforms all previous neural branching policies on real-world MILP instances and achieves superior computational efficiency compared to the advanced open-source solver SCIP. The source code can be accessed at https://github.com/doctor-watson626/Mamba-Branching/.

We propose a Geometry-Aware Policy Imitation (GPI) approach that rethinks imitation learning by treating demonstrations as geometric curves rather than collections of state–action samples. From these curves, GPI derives distance fields that give rise to two complementary control primitives: a progression flow that advances along expert trajectories and an attraction flow that corrects deviations. Their combination defines a controllable, non-parametric vector field that directly guides robot behavior. This formulation decouples metric learning from policy synthesis, enabling modular adaptation across low-dimensional robot states and high-dimensional perceptual inputs. GPI naturally supports multimodality by preserving distinct demonstrations as separate models and allows efficient composition of new demonstrations through simple additions to the distance field. We evaluate GPI in simulation and on real robots across diverse tasks. Experiments show that GPI achieves higher success rates than diffusion-based policies while running 20× faster, requiring less memory, and remaining robust to perturbations. These results establish GPI as an efficient, interpretable, and scalable alternative to generative approaches for robotic imitation learning.

Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy. Ensemble-based policy gradient methods, which employ multiple policies to collect diverse samples, have recently been proposed to promote exploration. However, merely broadening the exploration space does not always enhance learning capability, since excessive exploration can reduce exploration quality or compromise training stability. In this work, we theoretically analyze the impact of inter-policy diversity on learning efficiency in policy ensembles, and propose Coupled Policy Optimization (CPO), which regulates diversity through KL constraints between policies. The proposed method enables effective exploration and outperforms strong baselines such as SAPG, PBT, and PPO across multiple dexterous manipulation tasks in both sample efficiency and final performance. Furthermore, analysis of policy diversity and effective sample size during training reveals that follower policies naturally distribute around the leader, demonstrating the emergence of structured and efficient exploratory behavior. Our results indicate that diverse exploration under appropriate regulation is key to achieving stable and sample-efficient learning in ensemble policy gradient methods.

Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the prevailing paradigm relies exclusively on sparse outcome rewards and lacks consideration of the particularity of tool-use tasks, inflating policy-gradient variance and resulting in inefficient training. To better understand and address these challenges, we first establish a theoretical link between policy entropy and training stability of tool-use tasks, which reveals that structured, low-entropy tokens are primary determinants of rewards. Motivated by this insight, we propose Reshaped Token-level policy gradients (ResT) for tool-use tasks. ResT reshapes the policy gradient through entropy-informed token reweighting, progressively upweighting reasoning tokens as training proceeds. This scheme enables a smooth shift from structural correctness to semantic reasoning and stabilizes convergence in multi-turn tool-use tasks. Evaluation on BFCL and API-Bank shows that ResT outperforms other strong baselines, outperforming prior methods by up to 8.76%. When fine-tuned on a 4B base LLM, ResT further surpasses GPT-4o by 4.11% on single-turn tasks and 1.50% on multi-turn base tasks. Code is available at https://github.com/1229095296/ResT_Tool_use_LLM.

A fine-grained data recipe is crucial for pre-training large language models (LLMs), as it can significantly enhance training efficiency and model performance. One important ingredient in the recipe is to select samples based on scores produced by defined rules, LLM judgment, or statistical information in embeddings, which can be roughly categorized into quality and diversity metrics. Due to the high computational cost when applied to trillion-scale token pre-training datasets such as FineWeb and DCLM, these two or more types of metrics are rarely considered jointly in a single selection process. However, in our empirical study, selecting samples based on quality metrics exhibit severe diminishing returns during long-term pre-training, while selecting on diversity metrics removes too many valuable high-quality samples, both of which limit pre-trained LLMs' capabilities. Therefore, we introduce DATAMASK, a novel and efficient joint learning framework designed for large-scale pre-training data selection that can simultaneously optimize multiple types of metrics in a unified process, with this study focusing specifically on quality and diversity metrics. DATAMASK approaches the selection process as a mask learning problem, involving iterative sampling of data masks, computation of policy gradients based on predefined objectives with sampled masks, and updating of mask sampling logits. Through policy gradient-based optimization and various acceleration enhancements, it significantly reduces selection time by 98.9% compared to greedy algorithm, enabling our study to explore joint learning within trillion-scale tokens. With DATAMASK, we select a subset of about 10% from the 15 trillion-token FineWeb dataset, termed FineWeb-Mask. Evaluated across 12 diverse tasks, this high-quality and diverse subset achieves significant improvements of 3.2% on a 1.5B dense model and 1.9% on a 7B MoE model after pre-training with hundreds of billions of tokens, demonstrating its effectiveness.

Recent advances in hierarchical robot systems leverage a high-level planner to propose task plans and a low-level policy to generate robot actions. This design allows training the planner on action-free or even non-robot data sources (e.g., videos), providing transferable high-level guidance. Nevertheless, grounding these high-level plans into executable actions remains challenging, especially with the limited availability of high-quality robot data. To this end, we propose to improve the low-level policy through online interactions. Specifically, our approach collects online rollouts, retrospectively annotates the corresponding high-level goals from achieved outcomes, and aggregates these hindsight-relabeled experiences to update a goal-conditioned imitation policy. Our method, Hindsight Flow-conditioned Online Imitation (HinFlow), instantiates this idea with 2D point flows as the high-level planner. Across diverse manipulation tasks in both simulation and physical world, our method achieves more than $2\times$ performance improvement over the base policy, significantly outperforming the existing methods. Moreover, our framework enables policy acquisition from planners trained on cross-embodiment video data, demonstrating its potential for scalable and transferable robot learning.